Compare commits
2
Commits
v0.1.5
..
8a220a8810
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
8a220a8810 | ||
|
|
1864612d64 |
+1
-1
@@ -1,5 +1,5 @@
|
|||||||
# claude
|
# claude
|
||||||
.claude/
|
CLAUDE.md
|
||||||
|
|
||||||
# python
|
# python
|
||||||
__pycache__/
|
__pycache__/
|
||||||
|
|||||||
@@ -11,19 +11,17 @@ and storage-agnostic.
|
|||||||
`requirements.txt`:
|
`requirements.txt`:
|
||||||
|
|
||||||
```
|
```
|
||||||
envelope_crypto @ git+ssh://git@git.rethinkstudios.io/rethink-public/envelope_crypto.git@v0.1.5
|
envelope_crypto @ git+ssh://git@git.rethinkstudios.io/rethink-public/envelope_crypto.git@v0.1.0
|
||||||
```
|
```
|
||||||
|
|
||||||
Direct:
|
Direct:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
pip install "envelope_crypto @ git+ssh://git@git.rethinkstudios.io/rethink-public/envelope_crypto.git@v0.1.5"
|
pip install "envelope_crypto @ git+ssh://git@git.rethinkstudios.io/rethink-public/envelope_crypto.git@v0.1.0"
|
||||||
```
|
```
|
||||||
|
|
||||||
Requires `cryptography` (pulled transitively).
|
Requires `cryptography` (pulled transitively).
|
||||||
|
|
||||||
Drop the `@v0.1.5` suffix from the line above to install the latest unpinned.
|
|
||||||
|
|
||||||
## First-time setup
|
## First-time setup
|
||||||
|
|
||||||
Run once, ever, to create the data key and authorize the first system. You need an
|
Run once, ever, to create the data key and authorize the first system. You need an
|
||||||
@@ -39,10 +37,10 @@ openssl rsa -in local_priv.pem -pubout -out local_pub.pem
|
|||||||
from envelope_crypto import EnvelopeCrypto
|
from envelope_crypto import EnvelopeCrypto
|
||||||
|
|
||||||
# generate the DEK and wrap it for this system in one call
|
# generate the DEK and wrap it for this system in one call
|
||||||
crypto, fingerprint, wrapped = EnvelopeCrypto.bootstrap("public_key.pem")
|
crypto, fingerprint, wrapped = EnvelopeCrypto.bootstrap(cfg.local_pub)
|
||||||
|
|
||||||
# verify the keypair actually round-trips BEFORE storing anything
|
# verify the keypair actually round-trips BEFORE storing anything
|
||||||
crypto.self_test("public_key.pem", "private_key.pem") # raises if keys don't pair
|
crypto.self_test(cfg.local_pub, cfg.local_priv) # raises if keys don't pair
|
||||||
|
|
||||||
# store the wrapped key — this is now the ONLY record of the DEK
|
# store the wrapped key — this is now the ONLY record of the DEK
|
||||||
await db.create_document("keys", {"_id": fingerprint, "key": wrapped})
|
await db.create_document("keys", {"_id": fingerprint, "key": wrapped})
|
||||||
@@ -55,24 +53,17 @@ re-derived each boot by unwrapping. **Never persist the plaintext key.**
|
|||||||
|
|
||||||
```python
|
```python
|
||||||
crypto = EnvelopeCrypto()
|
crypto = EnvelopeCrypto()
|
||||||
fingerprint = crypto.get_rsa_key_fingerprint("public_key.pem")
|
fingerprint = crypto.get_rsa_key_fingerprint(cfg.local_pub)
|
||||||
record = await db.get_document("keys", {"_id": fingerprint})
|
record = await db.get_document("keys", {"_id": fingerprint})
|
||||||
if not record:
|
if not record:
|
||||||
raise RuntimeError("this system is not authorized")
|
raise RuntimeError("this system is not authorized")
|
||||||
crypto.initialize(crypto.decrypt_aes_key_with_rsa(record["key"], "private_key.pem"))
|
crypto.initialize(crypto.decrypt_aes_key_with_rsa(record["key"], cfg.local_priv))
|
||||||
bot.crypto = crypto
|
bot.crypto = crypto
|
||||||
```
|
```
|
||||||
|
|
||||||
The `keys` schema (`_id` = fingerprint, `key` = wrapped) is the **caller's** choice;
|
The `keys` schema (`_id` = fingerprint, `key` = wrapped) is the **caller's** choice;
|
||||||
this lib only produces `(fingerprint, wrapped_key)`.
|
this lib only produces `(fingerprint, wrapped_key)`.
|
||||||
|
|
||||||
`decrypt_aes_key_with_rsa` (like `encrypt_aes_key_with_rsa` and
|
|
||||||
`get_rsa_key_fingerprint`) takes `is_file` (default `True`). Pass `is_file=False` to
|
|
||||||
hand it PEM/OpenSSH key data directly — e.g. a private key sourced from a vault —
|
|
||||||
instead of a file path. `self_test` threads the same `is_file` through to both the
|
|
||||||
public and private key it loads, so `self_test(pub_pem, priv_pem, is_file=False)`
|
|
||||||
round-trips two in-memory PEM strings rather than treating them as paths.
|
|
||||||
|
|
||||||
## Encrypt / decrypt
|
## Encrypt / decrypt
|
||||||
|
|
||||||
```python
|
```python
|
||||||
@@ -80,16 +71,9 @@ enc = crypto.encrypt_data({"ssn": "..."}) # -> {"secure": True, "iv": ...,
|
|||||||
plain = crypto.decrypt_data(enc) # -> {"ssn": "..."}
|
plain = crypto.decrypt_data(enc) # -> {"ssn": "..."}
|
||||||
```
|
```
|
||||||
|
|
||||||
Dict keys must be `str`. `encrypt_data` raises `TypeError` on a non-str key (e.g. an
|
|
||||||
int-keyed dict of Discord snowflakes) instead of silently stringifying it — the
|
|
||||||
underlying JSON encoding has no other key type, so a coerced key would come back out
|
|
||||||
of `decrypt_data` as a `str` and no longer match the original lookup key.
|
|
||||||
|
|
||||||
For whole records: `decrypt_record(crypto, doc)` decrypts every `{secure, iv, data}`
|
For whole records: `decrypt_record(crypto, doc)` decrypts every `{secure, iv, data}`
|
||||||
field (nested up to `traversal_level`, default 2); `is_encrypted_record(doc)` reports
|
field (nested up to `traversal_level`, default 2); `is_encrypted_record(doc)` reports
|
||||||
whether any encrypted field exists. Both also detect `doc` itself being a bare
|
whether any encrypted field exists.
|
||||||
`{secure, iv, data}` blob (the file-storage pattern below, where the blob IS the whole
|
|
||||||
document) — not just blobs nested under a key.
|
|
||||||
|
|
||||||
```python
|
```python
|
||||||
from envelope_crypto import is_encrypted_record, decrypt_record
|
from envelope_crypto import is_encrypted_record, decrypt_record
|
||||||
@@ -98,11 +82,6 @@ if is_encrypted_record(doc):
|
|||||||
doc = decrypt_record(crypto, doc)
|
doc = decrypt_record(crypto, doc)
|
||||||
```
|
```
|
||||||
|
|
||||||
`is_encrypted_record` falls back to an unbounded-depth scan once `traversal_level` is
|
|
||||||
exhausted, so it reliably reports `True` for a blob left behind by a shallower
|
|
||||||
`decrypt_record`/`reencrypt` call — safe to use as a leftover-detecting audit after
|
|
||||||
rotation, regardless of how deep the blob is nested.
|
|
||||||
|
|
||||||
Naming aliases (same objects): `EnvelopeCrypto` = `DocumentCrypto` = `RecordCrypto`
|
Naming aliases (same objects): `EnvelopeCrypto` = `DocumentCrypto` = `RecordCrypto`
|
||||||
= `PCICrypto` (deprecated legacy alias). `decrypt_record` = `decrypt_document` =
|
= `PCICrypto` (deprecated legacy alias). `decrypt_record` = `decrypt_document` =
|
||||||
`decrypt_dict`; `is_encrypted_record` = `is_encrypted_document` = `is_encrypted_dict`.
|
`decrypt_dict`; `is_encrypted_record` = `is_encrypted_document` = `is_encrypted_dict`.
|
||||||
@@ -148,14 +127,7 @@ for fingerprint, wrapped_key in wrapped.items():
|
|||||||
|
|
||||||
`reencrypt(source_crypto, record)` is a method on the **destination** (new-key)
|
`reencrypt(source_crypto, record)` is a method on the **destination** (new-key)
|
||||||
instance: it decrypts each encrypted field with `source_crypto` (old key) and
|
instance: it decrypts each encrypted field with `source_crypto` (old key) and
|
||||||
re-encrypts with itself. Only `{secure, ...}` fields are touched — including `record`
|
re-encrypts with itself. Only `{secure, ...}` fields are touched.
|
||||||
itself if it IS a `{secure, iv, data}` blob (the file-storage pattern).
|
|
||||||
|
|
||||||
Rotation must fail loud: a per-field decrypt failure raises, and so does a blob nested
|
|
||||||
deeper than `traversal_level` — silently leaving it under the old key would strand it
|
|
||||||
once the old key's wrapped-key record is deleted below. If you nest blobs deeper than
|
|
||||||
the default `traversal_level=2`, pass a higher `traversal_level` or flatten the record
|
|
||||||
first.
|
|
||||||
|
|
||||||
## Storage patterns
|
## Storage patterns
|
||||||
|
|
||||||
@@ -180,4 +152,4 @@ The lib never touches a database; only the caller's storage layer differs.
|
|||||||
|
|
||||||
## Versioning
|
## Versioning
|
||||||
|
|
||||||
Releases are tagged `vX.Y.Z`. The install line above pins a release; drop the `@vX.Y.Z` suffix to install the latest unpinned. Pin deliberately for reproducible installs.
|
Tagged `vX.Y.Z`. Pin the tag in `requirements.txt`.
|
||||||
|
|||||||
+1
-1
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
|
|||||||
|
|
||||||
[project]
|
[project]
|
||||||
name = "envelope_crypto"
|
name = "envelope_crypto"
|
||||||
version = "0.1.5"
|
version = "0.1.0"
|
||||||
description = "Envelope encryption (RSA-OAEP wrapped AES-256-GCM) for dict records — config-free, storage-agnostic, installable."
|
description = "Envelope encryption (RSA-OAEP wrapped AES-256-GCM) for dict records — config-free, storage-agnostic, installable."
|
||||||
requires-python = ">=3.10"
|
requires-python = ">=3.10"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
|
|||||||
@@ -17,15 +17,15 @@ envelope-encryption pattern used by KMS-style systems.
|
|||||||
first-time setup: generate the DEK and wrap it for the first system in one call,
|
first-time setup: generate the DEK and wrap it for the first system in one call,
|
||||||
then verify the pipeline before storing anything:
|
then verify the pipeline before storing anything:
|
||||||
|
|
||||||
crypto, fingerprint, wrapped = EnvelopeCrypto.bootstrap("public_key.pem")
|
crypto, fingerprint, wrapped = EnvelopeCrypto.bootstrap(cfg.local_pub)
|
||||||
crypto.self_test("public_key.pem", "private_key.pem") # raises if anything is wrong
|
crypto.self_test(cfg.local_pub, cfg.local_priv) # raises if anything is wrong
|
||||||
caller_store({"_id": fingerprint, "key": wrapped}) # the only record of the DEK
|
caller_store({"_id": fingerprint, "key": wrapped}) # the only record of the DEK
|
||||||
|
|
||||||
boot (already set up): fingerprint own pubkey, fetch the wrapped DEK, unwrap:
|
boot (already set up): fingerprint own pubkey, fetch the wrapped DEK, unwrap:
|
||||||
|
|
||||||
fp = crypto.get_rsa_key_fingerprint("public_key.pem")
|
fp = crypto.get_rsa_key_fingerprint(cfg.local_pub)
|
||||||
record = caller_lookup(fp)
|
record = caller_lookup(fp)
|
||||||
crypto.initialize(crypto.decrypt_aes_key_with_rsa(record["key"], "private_key.pem"))
|
crypto.initialize(crypto.decrypt_aes_key_with_rsa(record["key"], cfg.local_priv))
|
||||||
|
|
||||||
authorize another system (this instance must already hold the DEK):
|
authorize another system (this instance must already hold the DEK):
|
||||||
|
|
||||||
@@ -44,36 +44,22 @@ set, then re-encrypt existing records old -> new:
|
|||||||
for record in caller_iter():
|
for record in caller_iter():
|
||||||
caller_update(new_crypto.reencrypt(crypto, record))
|
caller_update(new_crypto.reencrypt(crypto, record))
|
||||||
|
|
||||||
reencrypt/is_encrypted_record/decrypt_record all detect a bare {secure, iv, data}
|
|
||||||
blob used AS the whole record (the file-storage pattern), not just blobs nested
|
|
||||||
under a key. reencrypt fails loud (raises) rather than silently leaving a field
|
|
||||||
under the old key — including when a blob sits deeper than `traversal_level`;
|
|
||||||
is_encrypted_record falls back to an unbounded-depth scan past traversal_level so
|
|
||||||
it reliably catches leftovers as a post-rotation audit.
|
|
||||||
|
|
||||||
config-free: the host supplies the DEK and RSA key paths; this lib never imports
|
config-free: the host supplies the DEK and RSA key paths; this lib never imports
|
||||||
config, configures logging, or touches a database. storage-agnostic — the
|
config, configures logging, or touches a database. storage-agnostic — the
|
||||||
encrypted blob is a plain dict; store it in mongo, a sql json column, or a file.
|
encrypted blob is a plain dict; store it in mongo, a sql json column, or a file.
|
||||||
|
|
||||||
encrypt_data/decrypt_data round-trip a dict only when every key is a str —
|
|
||||||
json (the wire format under the hood) has no other key type, so encrypt_data
|
|
||||||
raises TypeError on a non-str key (e.g. an int-keyed dict of discord snowflakes)
|
|
||||||
rather than silently stringifying it and losing the original key on decrypt.
|
|
||||||
|
|
||||||
naming: EnvelopeCrypto is canonical. PCICrypto / DocumentCrypto / RecordCrypto are
|
naming: EnvelopeCrypto is canonical. PCICrypto / DocumentCrypto / RecordCrypto are
|
||||||
aliases (PCICrypto is a deprecated legacy alias). the document/record/dict
|
aliases (PCICrypto is a deprecated legacy alias). the document/record/dict
|
||||||
function variants are the same functions — use whichever fits your storage.
|
function variants are the same functions — use whichever fits your storage.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
import os
|
import os
|
||||||
import copy
|
|
||||||
import json
|
import json
|
||||||
import base64
|
import base64
|
||||||
import hashlib
|
import hashlib
|
||||||
import logging
|
import logging
|
||||||
from typing import Any, Dict, List, Optional, Tuple, Union
|
from typing import Any, Dict, List, Optional, Tuple, Union
|
||||||
|
|
||||||
from cryptography.exceptions import UnsupportedAlgorithm
|
|
||||||
from cryptography.hazmat.primitives import hashes, serialization
|
from cryptography.hazmat.primitives import hashes, serialization
|
||||||
from cryptography.hazmat.primitives.asymmetric import padding
|
from cryptography.hazmat.primitives.asymmetric import padding
|
||||||
from cryptography.hazmat.primitives.ciphers.aead import AESGCM
|
from cryptography.hazmat.primitives.ciphers.aead import AESGCM
|
||||||
@@ -82,83 +68,6 @@ from cryptography.hazmat.primitives.serialization import load_ssh_public_key
|
|||||||
_log = logging.getLogger(__name__)
|
_log = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
|
||||||
def _load_private_key(key_data: bytes, pw: Optional[bytes]):
|
|
||||||
"""load a PEM or OpenSSH private key, normalizing the missing-password error
|
|
||||||
|
|
||||||
cryptography raises TypeError when a key is encrypted but no password was given
|
|
||||||
(PEM raises it on the first call; OpenSSH raises it inside the openssh fallback).
|
|
||||||
both are normalized to a clear ValueError so callers see one error type.
|
|
||||||
"""
|
|
||||||
try:
|
|
||||||
return serialization.load_pem_private_key(key_data, password=pw)
|
|
||||||
except ValueError as error:
|
|
||||||
if b"BEGIN OPENSSH PRIVATE KEY" in key_data:
|
|
||||||
try:
|
|
||||||
return serialization.load_ssh_private_key(key_data, password=pw)
|
|
||||||
except TypeError as ssh_error:
|
|
||||||
raise ValueError(
|
|
||||||
"private key is encrypted but no password was provided"
|
|
||||||
) from ssh_error
|
|
||||||
if pw is not None:
|
|
||||||
# a password was given but the PEM load still failed — most likely a wrong
|
|
||||||
# password; give a clearer message than cryptography's raw "Bad decrypt"
|
|
||||||
raise ValueError("could not load private key (wrong password or malformed key)") from error
|
|
||||||
raise error
|
|
||||||
except TypeError as error:
|
|
||||||
raise ValueError(
|
|
||||||
"private key is encrypted but no password was provided"
|
|
||||||
) from error
|
|
||||||
|
|
||||||
|
|
||||||
def _fingerprint_of(public_key) -> str:
|
|
||||||
"""base64 SHA-256 fingerprint of an already-loaded public key
|
|
||||||
|
|
||||||
factored so callers that already hold a loaded key (e.g. encrypt_aes_key_with_rsa)
|
|
||||||
don't re-open and re-parse the key file just to fingerprint it.
|
|
||||||
"""
|
|
||||||
key_bytes = public_key.public_bytes(
|
|
||||||
encoding=serialization.Encoding.DER,
|
|
||||||
format=serialization.PublicFormat.SubjectPublicKeyInfo,
|
|
||||||
)
|
|
||||||
digest = hashes.Hash(hashes.SHA256())
|
|
||||||
digest.update(key_bytes)
|
|
||||||
return base64.b64encode(digest.finalize()).decode()
|
|
||||||
|
|
||||||
|
|
||||||
def _is_blob(value: Any) -> bool:
|
|
||||||
"""return whether value has the {secure, iv, data} encrypted-blob shape"""
|
|
||||||
return isinstance(value, dict) and value.get("secure") is True and "iv" in value and "data" in value
|
|
||||||
|
|
||||||
|
|
||||||
def _has_encrypted_field(record: Any) -> bool:
|
|
||||||
"""unbounded-depth scan: does record (or anything nested under it) contain a blob
|
|
||||||
|
|
||||||
used to detect a blob left behind by a depth-limited traversal — no traversal_level
|
|
||||||
cutoff here, since the whole point is to catch what a bounded pass would miss.
|
|
||||||
"""
|
|
||||||
if not isinstance(record, dict):
|
|
||||||
return False
|
|
||||||
if _is_blob(record):
|
|
||||||
return True
|
|
||||||
return any(_has_encrypted_field(value) for value in record.values())
|
|
||||||
|
|
||||||
|
|
||||||
def _load_public_key(key_data: bytes):
|
|
||||||
"""load a PEM or OpenSSH public key, normalizing non-key input to ValueError
|
|
||||||
|
|
||||||
load_ssh_public_key raises UnsupportedAlgorithm (not ValueError) on non-SSH/garbage
|
|
||||||
input; normalize it so a bad public key always surfaces as a clear ValueError,
|
|
||||||
consistent with the private-key path.
|
|
||||||
"""
|
|
||||||
try:
|
|
||||||
return serialization.load_pem_public_key(key_data)
|
|
||||||
except ValueError:
|
|
||||||
try:
|
|
||||||
return load_ssh_public_key(key_data)
|
|
||||||
except (UnsupportedAlgorithm, ValueError) as error:
|
|
||||||
raise ValueError("not a valid PEM or OpenSSH public key") from error
|
|
||||||
|
|
||||||
|
|
||||||
class EnvelopeCrypto:
|
class EnvelopeCrypto:
|
||||||
"""hybrid RSA/AES-256-GCM envelope encryption for dict records
|
"""hybrid RSA/AES-256-GCM envelope encryption for dict records
|
||||||
|
|
||||||
@@ -193,11 +102,7 @@ class EnvelopeCrypto:
|
|||||||
round-trips sample data through this instance's DEK, then wraps the DEK
|
round-trips sample data through this instance's DEK, then wraps the DEK
|
||||||
with the public key and unwraps with the private key, confirming they
|
with the public key and unwraps with the private key, confirming they
|
||||||
match. run after bootstrap (or anytime as a health check) to catch a bad
|
match. run after bootstrap (or anytime as a health check) to catch a bad
|
||||||
keypair or wrong key path before relying on it. is_file (default True) is
|
keypair or wrong key path before relying on it. returns True on success.
|
||||||
threaded through to both the public and private key loads, so
|
|
||||||
is_file=False correctly treats both rsa_public_key and rsa_private_key as
|
|
||||||
in-memory PEM/OpenSSH data rather than opening either as a file path.
|
|
||||||
returns True on success.
|
|
||||||
"""
|
"""
|
||||||
if not self.master_key:
|
if not self.master_key:
|
||||||
raise ValueError("self_test: not initialized with a key")
|
raise ValueError("self_test: not initialized with a key")
|
||||||
@@ -208,7 +113,7 @@ class EnvelopeCrypto:
|
|||||||
|
|
||||||
_, wrapped = self.encrypt_aes_key_with_rsa(self.master_key, rsa_public_key, is_file=is_file)
|
_, wrapped = self.encrypt_aes_key_with_rsa(self.master_key, rsa_public_key, is_file=is_file)
|
||||||
try:
|
try:
|
||||||
recovered = self.decrypt_aes_key_with_rsa(wrapped, rsa_private_key, is_file=is_file, password=password)
|
recovered = self.decrypt_aes_key_with_rsa(wrapped, rsa_private_key, password=password)
|
||||||
except Exception as error:
|
except Exception as error:
|
||||||
raise RuntimeError(
|
raise RuntimeError(
|
||||||
"self_test: key unwrap failed (public/private keys do not pair, "
|
"self_test: key unwrap failed (public/private keys do not pair, "
|
||||||
@@ -242,18 +147,9 @@ class EnvelopeCrypto:
|
|||||||
return key
|
return key
|
||||||
|
|
||||||
def get_rsa_key_fingerprint(
|
def get_rsa_key_fingerprint(
|
||||||
self, key_path_or_data: str, is_private: bool = False, is_file: bool = True,
|
self, key_path_or_data: str, is_private: bool = False, is_file: bool = True
|
||||||
password: Optional[str] = None,
|
|
||||||
) -> str:
|
) -> str:
|
||||||
"""return a base64 SHA-256 fingerprint of an RSA key for identification
|
"""return a base64 SHA-256 fingerprint of an RSA key for identification"""
|
||||||
|
|
||||||
for an encrypted private key (is_private=True), pass its `password`; an
|
|
||||||
unencrypted key ignores it. fingerprinting always uses the public half, so a
|
|
||||||
private and its public key produce the same fingerprint. PEM and OpenSSH
|
|
||||||
private-key formats are both accepted (mirrors decrypt_aes_key_with_rsa). an
|
|
||||||
encrypted key with no/wrong password raises ValueError with a clear message
|
|
||||||
(cryptography raises TypeError for the missing-password case — normalized here).
|
|
||||||
"""
|
|
||||||
if is_file:
|
if is_file:
|
||||||
with open(key_path_or_data, "rb") as key_file:
|
with open(key_path_or_data, "rb") as key_file:
|
||||||
key_data = key_file.read()
|
key_data = key_file.read()
|
||||||
@@ -265,13 +161,21 @@ class EnvelopeCrypto:
|
|||||||
)
|
)
|
||||||
|
|
||||||
if is_private:
|
if is_private:
|
||||||
pw = password.encode() if password else None
|
private_key = serialization.load_pem_private_key(key_data, password=None)
|
||||||
private_key = _load_private_key(key_data, pw)
|
|
||||||
public_key = private_key.public_key()
|
public_key = private_key.public_key()
|
||||||
else:
|
else:
|
||||||
public_key = _load_public_key(key_data)
|
try:
|
||||||
|
public_key = serialization.load_pem_public_key(key_data)
|
||||||
|
except ValueError:
|
||||||
|
public_key = load_ssh_public_key(key_data)
|
||||||
|
|
||||||
fingerprint = _fingerprint_of(public_key)
|
key_bytes = public_key.public_bytes(
|
||||||
|
encoding=serialization.Encoding.DER,
|
||||||
|
format=serialization.PublicFormat.SubjectPublicKeyInfo,
|
||||||
|
)
|
||||||
|
digest = hashes.Hash(hashes.SHA256())
|
||||||
|
digest.update(key_bytes)
|
||||||
|
fingerprint = base64.b64encode(digest.finalize()).decode()
|
||||||
_log.info("generated %s key fingerprint", "private" if is_private else "public")
|
_log.info("generated %s key fingerprint", "private" if is_private else "public")
|
||||||
return fingerprint
|
return fingerprint
|
||||||
|
|
||||||
@@ -285,7 +189,10 @@ class EnvelopeCrypto:
|
|||||||
else:
|
else:
|
||||||
key_data = rsa_key.encode() if isinstance(rsa_key, str) else rsa_key
|
key_data = rsa_key.encode() if isinstance(rsa_key, str) else rsa_key
|
||||||
|
|
||||||
public_key = _load_public_key(key_data)
|
try:
|
||||||
|
public_key = serialization.load_pem_public_key(key_data)
|
||||||
|
except ValueError:
|
||||||
|
public_key = load_ssh_public_key(key_data)
|
||||||
|
|
||||||
wrapped = public_key.encrypt(
|
wrapped = public_key.encrypt(
|
||||||
aes_key,
|
aes_key,
|
||||||
@@ -295,30 +202,29 @@ class EnvelopeCrypto:
|
|||||||
label=None,
|
label=None,
|
||||||
),
|
),
|
||||||
)
|
)
|
||||||
# fingerprint from the already-loaded public_key — no second open/parse of the file
|
fingerprint = self.get_rsa_key_fingerprint(rsa_key, is_private=False, is_file=is_file)
|
||||||
fingerprint = _fingerprint_of(public_key)
|
|
||||||
wrapped_b64 = base64.b64encode(wrapped).decode()
|
wrapped_b64 = base64.b64encode(wrapped).decode()
|
||||||
_log.info("wrapped data key for fingerprint %s", fingerprint[:8])
|
_log.info("wrapped data key for fingerprint %s", fingerprint[:8])
|
||||||
return fingerprint, wrapped_b64
|
return fingerprint, wrapped_b64
|
||||||
|
|
||||||
def decrypt_aes_key_with_rsa(
|
def decrypt_aes_key_with_rsa(
|
||||||
self, encrypted_key_base64: str, rsa_private_key: str,
|
self, encrypted_key_base64: str, rsa_private_key_path: str,
|
||||||
is_file: bool = True, password: Optional[str] = None,
|
password: Optional[str] = None,
|
||||||
) -> bytes:
|
) -> bytes:
|
||||||
"""unwrap an AES key with an RSA private key
|
"""unwrap an AES key with an RSA private key"""
|
||||||
|
with open(rsa_private_key_path, "rb") as key_file:
|
||||||
is_file defaults to True (rsa_private_key is a path), matching
|
key_data = key_file.read()
|
||||||
encrypt_aes_key_with_rsa / get_rsa_key_fingerprint; pass is_file=False to
|
try:
|
||||||
supply the PEM/OpenSSH key data directly (e.g. an in-memory or vault-sourced
|
private_key = serialization.load_pem_private_key(
|
||||||
key) instead of a file path.
|
key_data, password=password.encode() if password else None
|
||||||
"""
|
)
|
||||||
if is_file:
|
except ValueError as error:
|
||||||
with open(rsa_private_key, "rb") as key_file:
|
if b"BEGIN OPENSSH PRIVATE KEY" in key_data:
|
||||||
key_data = key_file.read()
|
private_key = serialization.load_ssh_private_key(
|
||||||
else:
|
key_data, password=password.encode() if password else None
|
||||||
key_data = rsa_private_key.encode() if isinstance(rsa_private_key, str) else rsa_private_key
|
)
|
||||||
pw = password.encode() if password else None
|
else:
|
||||||
private_key = _load_private_key(key_data, pw)
|
raise error
|
||||||
|
|
||||||
wrapped = base64.b64decode(encrypted_key_base64)
|
wrapped = base64.b64decode(encrypted_key_base64)
|
||||||
aes_key = private_key.decrypt(
|
aes_key = private_key.decrypt(
|
||||||
@@ -361,30 +267,9 @@ class EnvelopeCrypto:
|
|||||||
return new_key, wrapped
|
return new_key, wrapped
|
||||||
|
|
||||||
def encrypt_data(self, data: Union[Dict[str, Any], str]) -> Dict[str, str]:
|
def encrypt_data(self, data: Union[Dict[str, Any], str]) -> Dict[str, str]:
|
||||||
"""encrypt a dict or string under the data key with a unique IV
|
"""encrypt a dict or string under the data key with a unique IV"""
|
||||||
|
|
||||||
dict keys must be str: json.dumps silently stringifies int/float/bool/None
|
|
||||||
keys (e.g. a snowflake-int-keyed dict), which would make decrypt_data return
|
|
||||||
a dict that no longer matches the original by key type or identity — a
|
|
||||||
non-str key is rejected here instead, so the failure is loud at encrypt
|
|
||||||
time rather than a silent lookup miss after decrypt.
|
|
||||||
"""
|
|
||||||
if not self.master_key:
|
if not self.master_key:
|
||||||
raise ValueError("not initialized with data key")
|
raise ValueError("not initialized with data key")
|
||||||
if not isinstance(data, (dict, str)):
|
|
||||||
# a non-dict/non-str would .encode()-fail with an opaque AttributeError below;
|
|
||||||
# reject it clearly (decrypt_data only round-trips dict or str anyway)
|
|
||||||
raise TypeError(f"encrypt_data expects a dict or str, got {type(data).__name__}")
|
|
||||||
if isinstance(data, dict):
|
|
||||||
non_str_keys = [key for key in data if not isinstance(key, str)]
|
|
||||||
if non_str_keys:
|
|
||||||
# json.dumps would silently stringify these (int/float/bool/None keys),
|
|
||||||
# corrupting the round-trip (decrypt_data would return a dict keyed by
|
|
||||||
# the stringified value) — fail loud instead of coercing
|
|
||||||
raise TypeError(
|
|
||||||
"encrypt_data requires str dict keys, got non-str key(s): "
|
|
||||||
f"{[type(key).__name__ for key in non_str_keys]}"
|
|
||||||
)
|
|
||||||
|
|
||||||
data_str = json.dumps(data) if isinstance(data, dict) else data
|
data_str = json.dumps(data) if isinstance(data, dict) else data
|
||||||
iv = os.urandom(12)
|
iv = os.urandom(12)
|
||||||
@@ -397,36 +282,18 @@ class EnvelopeCrypto:
|
|||||||
}
|
}
|
||||||
|
|
||||||
def decrypt_data(self, encrypted_data: Dict[str, str]) -> Union[Dict[str, Any], str]:
|
def decrypt_data(self, encrypted_data: Dict[str, str]) -> Union[Dict[str, Any], str]:
|
||||||
"""decrypt a {secure, iv, data} blob; returns the original dict or string
|
"""decrypt a {secure, iv, data} blob; returns the original dict or string"""
|
||||||
|
|
||||||
`encrypt_data` only json-encodes dicts (a string is stored verbatim), so decrypt
|
|
||||||
only treats a json-OBJECT plaintext as a dict and returns everything else as the
|
|
||||||
raw string. this keeps the type faithful for the common cases: a string that is
|
|
||||||
json-shaped but NOT an object ('123'->'123', 'true'->'true', '[1,2]'->'[1,2]')
|
|
||||||
round-trips as a STRING, not an int/bool/list. the one irreducible ambiguity: a
|
|
||||||
string whose exact value is a json OBJECT ('{"a":1}') decrypts to a dict, because
|
|
||||||
without a type marker it is indistinguishable from a stored dict — don't store a
|
|
||||||
bare string that is a json object if you need it back as a string. existing stored
|
|
||||||
blobs are unaffected — a dict was stored as a json object and still parses to a dict.
|
|
||||||
dict KEYS round-trip faithfully only because encrypt_data now requires str keys —
|
|
||||||
json has no other key type, so this is the only shape decrypt_data ever sees.
|
|
||||||
"""
|
|
||||||
if not self.master_key:
|
if not self.master_key:
|
||||||
raise ValueError("not initialized with data key")
|
raise ValueError("not initialized with data key")
|
||||||
if not isinstance(encrypted_data, dict) or "iv" not in encrypted_data or "data" not in encrypted_data:
|
|
||||||
# a structurally-malformed blob would raise a raw KeyError/TypeError; surface
|
|
||||||
# a clear ValueError instead, matching the documented {secure, iv, data} shape
|
|
||||||
raise ValueError("decrypt_data expects a {secure, iv, data} blob")
|
|
||||||
|
|
||||||
iv = base64.b64decode(encrypted_data["iv"])
|
iv = base64.b64decode(encrypted_data["iv"])
|
||||||
ciphertext = base64.b64decode(encrypted_data["data"])
|
ciphertext = base64.b64decode(encrypted_data["data"])
|
||||||
aesgcm = AESGCM(self.master_key)
|
aesgcm = AESGCM(self.master_key)
|
||||||
plaintext = aesgcm.decrypt(iv, ciphertext, None).decode()
|
plaintext = aesgcm.decrypt(iv, ciphertext, None).decode()
|
||||||
try:
|
try:
|
||||||
parsed = json.loads(plaintext)
|
return json.loads(plaintext)
|
||||||
except json.JSONDecodeError:
|
except json.JSONDecodeError:
|
||||||
return plaintext
|
return plaintext
|
||||||
return parsed if isinstance(parsed, dict) else plaintext
|
|
||||||
|
|
||||||
def reencrypt(self, source_crypto: "EnvelopeCrypto", record: dict, traversal_level: int = 2) -> dict:
|
def reencrypt(self, source_crypto: "EnvelopeCrypto", record: dict, traversal_level: int = 2) -> dict:
|
||||||
"""re-encrypt a record's encrypted fields from source_crypto's key to this one's
|
"""re-encrypt a record's encrypted fields from source_crypto's key to this one's
|
||||||
@@ -434,43 +301,16 @@ class EnvelopeCrypto:
|
|||||||
self holds the destination (new) key; source_crypto holds the source (old)
|
self holds the destination (new) key; source_crypto holds the source (old)
|
||||||
key. only {secure, iv, data} fields are touched; plaintext fields are left
|
key. only {secure, iv, data} fields are touched; plaintext fields are left
|
||||||
as-is. returns a new dict; the input is not mutated. used during rotation.
|
as-is. returns a new dict; the input is not mutated. used during rotation.
|
||||||
|
|
||||||
if `record` itself is a {secure, iv, data} blob (the file-storage pattern, where
|
|
||||||
the blob IS the whole document) it is re-encrypted directly and the result is
|
|
||||||
returned in place of `record` — not nested under a key.
|
|
||||||
|
|
||||||
unlike decrypt_record (which logs a failed field and leaves it encrypted), a
|
|
||||||
per-field decrypt failure here RAISES — rotation must fail loud, since silently
|
|
||||||
keeping a field under the old key would lose it once the old key is retired. for
|
|
||||||
the same reason, a blob nested DEEPER than `traversal_level` also RAISES instead
|
|
||||||
of being silently left under the old key: the caller either needs a higher
|
|
||||||
`traversal_level` or must flatten the record before rotation.
|
|
||||||
|
|
||||||
traversal recurses into nested DICTS only; a blob nested inside a LIST is NOT
|
|
||||||
re-encrypted and is NOT covered by the depth-limit raise above. records in this
|
|
||||||
scheme key blobs by field name, not inside arrays, so this doesn't arise in
|
|
||||||
practice — but if you store list-nested blobs, flatten them to dict fields before
|
|
||||||
rotation or they'll be silently left under the old key.
|
|
||||||
"""
|
"""
|
||||||
if not self.master_key:
|
if not self.master_key:
|
||||||
raise ValueError("destination not initialized with data key")
|
raise ValueError("destination not initialized with data key")
|
||||||
|
|
||||||
if _is_blob(record):
|
result = record.copy()
|
||||||
return self.encrypt_data(source_crypto.decrypt_data(record))
|
|
||||||
|
|
||||||
result = copy.deepcopy(record)
|
|
||||||
for key, value in record.items():
|
for key, value in record.items():
|
||||||
if _is_blob(value):
|
if isinstance(value, dict) and value.get("secure") is True and "iv" in value and "data" in value:
|
||||||
result[key] = self.encrypt_data(source_crypto.decrypt_data(value))
|
result[key] = self.encrypt_data(source_crypto.decrypt_data(value))
|
||||||
elif isinstance(value, dict):
|
elif traversal_level > 0 and isinstance(value, dict):
|
||||||
if traversal_level > 0:
|
result[key] = self.reencrypt(source_crypto, value, traversal_level - 1)
|
||||||
result[key] = self.reencrypt(source_crypto, value, traversal_level - 1)
|
|
||||||
elif _has_encrypted_field(value):
|
|
||||||
raise ValueError(
|
|
||||||
f"reencrypt: field {key!r} contains an encrypted blob nested deeper "
|
|
||||||
"than traversal_level; increase traversal_level or flatten the record "
|
|
||||||
"before rotation — leaving it would strand the field under the old key"
|
|
||||||
)
|
|
||||||
return result
|
return result
|
||||||
|
|
||||||
|
|
||||||
@@ -483,46 +323,28 @@ PCICrypto = EnvelopeCrypto # deprecated legacy alias; remove after all systems
|
|||||||
def is_encrypted_record(record, traversal_level: int = 2) -> bool:
|
def is_encrypted_record(record, traversal_level: int = 2) -> bool:
|
||||||
"""return whether a record has any encrypted ({secure, iv, data}) fields
|
"""return whether a record has any encrypted ({secure, iv, data}) fields
|
||||||
|
|
||||||
checks `record` itself (the file-storage pattern stores the blob AS the whole
|
|
||||||
document, not nested under a key) as well as fields up to `traversal_level` deep.
|
|
||||||
beyond that bounded pass, this ALSO does an unbounded-depth scan before giving up —
|
|
||||||
so a blob left behind by a shallower decrypt_record/reencrypt call (nested deeper
|
|
||||||
than their traversal_level) is still reported as encrypted. this makes the function
|
|
||||||
safe to use as a leftover-detecting post-rotation audit: it never returns False for
|
|
||||||
a record that still contains a blob, at any depth.
|
|
||||||
|
|
||||||
aliases: is_encrypted_document, is_encrypted_dict — same function
|
aliases: is_encrypted_document, is_encrypted_dict — same function
|
||||||
"""
|
"""
|
||||||
if not isinstance(record, dict):
|
if not isinstance(record, dict):
|
||||||
return False
|
return False
|
||||||
|
|
||||||
if _is_blob(record):
|
|
||||||
return True
|
|
||||||
|
|
||||||
for value in record.values():
|
for value in record.values():
|
||||||
if _is_blob(value):
|
if isinstance(value, dict) and value.get("secure") is True:
|
||||||
return True
|
if "iv" in value and "data" in value:
|
||||||
|
return True
|
||||||
|
|
||||||
if traversal_level > 0:
|
if traversal_level > 0:
|
||||||
for value in record.values():
|
for value in record.values():
|
||||||
if isinstance(value, dict) and is_encrypted_record(value, traversal_level - 1):
|
if isinstance(value, dict) and is_encrypted_record(value, traversal_level - 1):
|
||||||
return True
|
return True
|
||||||
return False
|
return False
|
||||||
|
|
||||||
return any(_has_encrypted_field(value) for value in record.values())
|
|
||||||
|
|
||||||
|
|
||||||
def decrypt_record(crypto: EnvelopeCrypto, record, traversal_level: int = 2) -> Union[dict, Any]:
|
def decrypt_record(crypto: EnvelopeCrypto, record, traversal_level: int = 2) -> dict:
|
||||||
"""decrypt a record's encrypted fields into a new dict (up to traversal_level deep)
|
"""decrypt a record's encrypted fields into a new dict (up to traversal_level deep)
|
||||||
|
|
||||||
if `record` itself is a {secure, iv, data} blob (the file-storage pattern, where the
|
|
||||||
blob IS the whole document) it is decrypted directly and the decrypted value
|
|
||||||
(dict or string — see decrypt_data) is returned in place of `record`.
|
|
||||||
|
|
||||||
failures on a single field are logged and that field is left encrypted, so a
|
failures on a single field are logged and that field is left encrypted, so a
|
||||||
partial failure is visible (the {secure,...} blob remains) rather than silent. a
|
partial failure is visible (the {secure,...} blob remains) rather than silent.
|
||||||
failure decrypting `record` itself (the self-blob case above) is likewise logged
|
|
||||||
and the still-encrypted blob is returned unchanged.
|
|
||||||
|
|
||||||
aliases: decrypt_document, decrypt_dict — same function
|
aliases: decrypt_document, decrypt_dict — same function
|
||||||
"""
|
"""
|
||||||
@@ -531,16 +353,9 @@ def decrypt_record(crypto: EnvelopeCrypto, record, traversal_level: int = 2) ->
|
|||||||
if not isinstance(record, dict):
|
if not isinstance(record, dict):
|
||||||
return record
|
return record
|
||||||
|
|
||||||
if _is_blob(record):
|
result = record.copy()
|
||||||
try:
|
|
||||||
return crypto.decrypt_data(record)
|
|
||||||
except Exception:
|
|
||||||
_log.exception("failed to decrypt record")
|
|
||||||
return copy.deepcopy(record)
|
|
||||||
|
|
||||||
result = copy.deepcopy(record)
|
|
||||||
for key, value in record.items():
|
for key, value in record.items():
|
||||||
if _is_blob(value):
|
if isinstance(value, dict) and value.get("secure") is True and "iv" in value and "data" in value:
|
||||||
try:
|
try:
|
||||||
result[key] = crypto.decrypt_data(value)
|
result[key] = crypto.decrypt_data(value)
|
||||||
except Exception:
|
except Exception:
|
||||||
|
|||||||
Reference in New Issue
Block a user