ClawAudit verdict
say-hi-to-me
The skill provides companion-style check-ins and conversation, which seems to be within its legitimate purpose.
⚠ 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)
Long base64 string (100+ chars) — likely obfuscated payload
README.md · prose · downgraded · PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCA4OCA4OCI+
Instructs covert action — may act without user awareness
references/openclaw-heartbeat-integration.md · prose · downgraded · quietly
Python os.environ.get — reads environment variable
scripts/sync_heartbeat_md.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.