ClawAudit verdict
huo15-openclaw-openai-knowledge-base
The skill is used for building a knowledge base and does not contain any malicious code or intent.
⚠ 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.
Permission integrity
agent_memory
Findings (4)
References agent memory files
SKILL.md · code · daily_notes
References child_process — can spawn system processes
templates/wiki-schema.md · prose · downgraded · child_process
Python urllib.request — network access
scripts/kb-llm.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/kb-llm.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.