ClawAudit verdict
handover-hangover
The skill only creates and reads handoff files for session continuity and does not exfiltrate data or execute untrusted code.
⚠ 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 (6)
Writes to SKILL.md — self-modifying skill
CHANGELOG.md · prose · downgraded · SKILL.md`: system prompt with write
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
References child_process — can spawn system processes
CHANGELOG.md · prose · downgraded · child_process
Dynamic import() — loads module at runtime
tests/run-tests.sh · prose · downgraded · import('
References agent configuration files
CHANGELOG.md · prose · downgraded · CLAUDE.md
References agent memory files
README.md · prose · downgraded · MEMORY.md
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.