ClawAudit verdict
ssh-agentd-control
The skill manages and uses the local ssh-agentd, with no indication of malicious or deceptive 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)
References sudo — requests elevated privileges
SKILL.md · code · sudo
Possible hardcoded credential
scripts/api.sh · prose · downgraded · TOKEN="${SSH_AGENTD_TOKEN:-}
HTTP request to bare IP address — common in malicious payloads
scripts/api.sh · prose · downgraded · http://127.0.0.1
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.