ktg-plugin-marketplace/plugins/llm-security/hooks
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
..
scripts fix(llm-security): B2 block-mode blocks all detected trifectas, not only high-confidence 2026-04-20 00:04:36 +02:00
hooks.json feat(hooks): register PreCompact event in hooks.json 2026-04-17 14:45:13 +02:00