Commit graph

4 commits

Author SHA1 Message Date
Kjell Tore Guttormsen
36be963d4d fix(llm-security): B2 block-mode blocks all detected trifectas, not only high-confidence
Previously, `LLM_SECURITY_TRIFECTA_MODE=block` only exited 2 when the
detected trifecta was MCP-concentrated (all three legs via the same MCP
server) or involved sensitive-path + exfil. Distributed trifectas —
three legs originating from different tools, with a non-sensitive data
path and a non-sensitive exfiltration sink — were detected and warned
but not blocked. This mismatched the documented semantics of block mode
and gave operators a false sense of enforcement.

Change: remove the `(mcpInfo.concentrated || sensitiveExfil)` AND-gate
in the `TRIFECTA_MODE === 'block'` branch so any detected trifecta
blocks in block mode. Audit event `severity` still differentiates
critical (concentrated / sensitive-exfil) from high (distributed); the
blocked stderr message now explicitly names "Distributed trifecta:
three legs from different sources" when the confidence sub-signals
are absent.

Addresses critical review 2026-04-20 §2 B2 (HIGH) and §9 row 1
("enforces the Rule of Two").

Tests: 1 added (distributed trifecta in block mode now exits 2).
All 1495 tests pass.
2026-04-20 00:04:36 +02:00
Kjell Tore Guttormsen
8ec320f40c feat(governance): add policy-as-code — .llm-security/policy.json for distributable hook configuration
New policy-loader.mjs reads .llm-security/policy.json with deep-merge against
defaults that exactly match existing hardcoded values. Integrated into all 7 hooks:
- pre-prompt-inject-scan: injection.mode (env var still takes precedence)
- post-session-guard: trifecta.mode, window_size, long_horizon_window
- pre-edit-secrets: secrets.additional_patterns
- pre-bash-destructive: destructive.additional_blocked
- pre-write-pathguard: pathguard.additional_protected
- pre-install-supply-chain: supply_chain.additional_blocked_packages
- post-mcp-verify: mcp.volume_threshold_bytes, mcp.trusted_servers

Backward compatible: no policy file = identical behavior to v5.1.0.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-10 13:37:02 +02:00
Kjell Tore Guttormsen
269c14445c feat(governance): add structured JSONL audit trail with SIEM-ready schema
New audit-trail.mjs writes structured events to LLM_SECURITY_AUDIT_LOG path.
Integrated into post-session-guard at 6 warning emission points: trifecta,
escalation-after-input, data flow, volume threshold, slow-burn, behavioral drift.
No-op when env var not set — zero overhead for existing users.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-10 13:25:59 +02:00
Kjell Tore Guttormsen
f93d6abdae feat: initial open marketplace with llm-security, config-audit, ultraplan-local 2026-04-06 18:47:49 +02:00