AISentinel is an open-source security and observability layer for AI agents that evaluates every tool call against configurable YAML policies, allowing, blocking, or requiring human approval before the call executes. It writes an append-only, tamper-evident JSONL audit log of every decision and its rationale, and ships with built-in security policies out of the box. It runs locally with no telemetry sent to any external service.
Cognium trust score
63%
Tier
Scanned
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-08-30.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.