Compare commits

..

5 Commits

Author SHA1 Message Date
didericis-claude 00e50973c2 fix(dlp): skip projection passes when exact variant is safe-listed
lint / lint (push) Failing after 2m7s
test / unit (pull_request) Successful in 44s
test / integration (pull_request) Successful in 25s
When a supervisor-approved safe-token exactly matched an env secret
(Pass 1), Passes 2 & 3 (alnum projection) still ran and re-blocked on
the same value.  Track whether any variant was found-and-approved and
skip the projection passes for that secret in that case.
2026-06-25 02:33:34 +00:00
didericis-claude 8bd748f54f docs(prd): flip prd-new-strengthen-outbound-exfil-detection Draft → Active
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-25 02:31:21 +00:00
didericis-claude 99236d4a01 feat(egress): inject per-session canary token into sidecar and agent environments
EgressPlan gains a `canary: str` field (default "") populated in Egress.prepare()
using secrets.token_urlsafe(32).  Each launched bottle:

  - sidecar receives EGRESS_TOKEN_CANARY=<value> (literal env entry, scanned by
    existing known-secrets detector without any detector code changes)
  - agent receives BOT_BOTTLE_CANARY=<value> (visible fake secret that signals
    exfiltration with zero false positives if it appears in outbound traffic)

Docker compose and macos-container backends updated; smolmachines shares docker
compose and so picks this up automatically.  Unit tests cover canary uniqueness,
detection via scan_known_secrets, and EgressPlan backward-compat default.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-25 02:31:21 +00:00
didericis-claude aab450f2f7 feat(dlp): fragmentation resistance, entropy detector, broadened known-value scan
- _alnum_projection(): strip non-alphanumeric chars for separator-injection detection
- scan_known_secrets() gains two extra passes per secret after exact-variant matching:
  alnum-projection exact match (catches hyphens/spaces between secret chars) and a
  sliding-window partial-match scan (catches chunked substrings ≥ PARTIAL_MATCH_MIN_LEN)
- scan_known_secrets() accepts sensitive_prefixes param (default ("EGRESS_TOKEN_",))
  so redact_tokens and call-sites can extend the scanned env-var prefix set
- scan_entropy() warn-only detector flagging windows with Shannon entropy ≥ 5.5 bits/char
- "entropy" added to OUTBOUND_DETECTOR_NAMES; scan_outbound opts it in only when
  explicitly listed in dlp.outbound_detectors (never part of the default "all" set)
- scan_outbound reads BOT_BOTTLE_SENSITIVE_PREFIXES from environ to extend
  scan_known_secrets beyond EGRESS_TOKEN_* without schema changes
- Binary bodies decoded via latin-1 fallback (bijective byte↔codepoint) instead
  of utf-8 errors=replace, preserving ASCII secret strings in binary payloads

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-25 02:31:21 +00:00
didericis-claude 8fa075aa01 docs: draft PRD prd-new for strengthen-outbound-exfil-detection
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-25 02:22:20 +00:00
3 changed files with 1 additions and 35 deletions
@@ -19,7 +19,7 @@ import urllib.error
import urllib.request
from pathlib import Path
from ...deploy_key_provisioner import DeployKeyCollisionError, DeployKeyProvisioner
from ...deploy_key_provisioner import DeployKeyProvisioner
class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
@@ -71,11 +71,6 @@ class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
body = json.loads(resp.read())
except urllib.error.HTTPError as exc:
_body = _read_error_body(exc)
if exc.code == 422:
raise DeployKeyCollisionError(
f"deploy key collision for {owner_repo!r} "
f"(title={title!r}): key title or content already registered — {_body}"
) from exc
raise RuntimeError(
f"failed to create deploy key for {owner_repo}: "
f"HTTP {exc.code}{_body}"
-4
View File
@@ -11,10 +11,6 @@ from __future__ import annotations
from abc import ABC, abstractmethod
class DeployKeyCollisionError(RuntimeError):
"""Raised when a deploy key title or public key already exists on the repo."""
class DeployKeyProvisioner(ABC):
"""Manages a single deploy-key lifecycle on a remote forge."""
@@ -12,7 +12,6 @@ from bot_bottle.contrib.gitea.deploy_key_provisioner import (
GiteaDeployKeyProvisioner,
_split_owner_repo,
)
from bot_bottle.deploy_key_provisioner import DeployKeyCollisionError
def _provisioner() -> GiteaDeployKeyProvisioner:
@@ -101,30 +100,6 @@ class TestCreate(unittest.TestCase):
provisioner.create("owner/repo", "title")
self.assertIn("403", str(ctx.exception))
def test_create_raises_collision_error_on_422(self):
provisioner = _provisioner()
collision_body = json.dumps({
"errors": ["Key content already exists on this repository"],
"message": "422 Unprocessable Entity",
})
with patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.subprocess.run"
), patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.urllib.request.urlopen",
side_effect=_http_error(422, collision_body),
), patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.Path.read_bytes",
return_value=b"pk",
), patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.Path.read_text",
return_value="ssh-ed25519 AAAA\n",
):
with self.assertRaises(DeployKeyCollisionError) as ctx:
provisioner.create("owner/repo", "my-title")
msg = str(ctx.exception)
self.assertIn("owner/repo", msg)
self.assertIn("my-title", msg)
class TestDelete(unittest.TestCase):
def test_delete_calls_correct_endpoint(self):