ClawAudit verdict
spiritlab-library
The skill seems to be used for knowledge retrieval and does not show malicious behavior.
⚠ 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 (4)
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://101.43.156.136
Python urllib.request — network access
search.py · prose · downgraded · urllib.request
References agent memory files
search.py · prose · downgraded · MEMORY.md
Python shutil file operation — copies/moves/deletes files
search.py · prose · downgraded · shutil.copy(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.