ClawAudit verdict
phoenixclaw
A journaling skill that scans local session logs and memory files to generate markdown journals — all operations are local file reads/writes with no external exfiltration detected.
⚠ 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.
Findings (1)
References child_process — can spawn system processes
scripts/rolling-journal.js · 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.
Is this flag fair?
Thanks — recorded.