ClawAudit verdict

collect-session

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Collects session data and writes markdown/JSON files locally; it only contacts a locally‑hosted LiteLLM instance and does not exfiltrate data.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

70
security
60
transparency
70
maintenance

Findings (3)

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.LITELLM_API_KEY

Pattern match medium

References child_process — can spawn system processes

scripts/hook-handler.ts · prose · downgraded · child_process

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API