ClawAudit verdict

cyber-friending

cyber-friending-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill appears to be a legitimate tool for social interaction, with clear instructions and no malicious code.

⚠ 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.

78
security
90
transparency
70
maintenance

Findings (2)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://115.190.255.55

Pattern match low

References agent configuration files

SKILL.md · prose · downgraded · agent_config

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API