ClawAudit verdict
sql-memory
The skill seems to be focused on providing a semantic memory layer for OpenClaw agents, with no apparent 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 (3)
HTTP request to bare IP address — common in malicious payloads
knowledge-base/INFRASTRUCTURE.md · prose · downgraded · http://10.0.0.110
Popular HTTP library — network access
GETTING_STARTED.md · prose · downgraded · got
Python urllib.request — network access
tests/test_queue_verifier.py · prose · downgraded · urllib.request
Permissions & capabilities
No declared permissions — minimal attack surface.
network_in Is this flag fair?
Thanks — recorded.