Caveat verdict
create_agent
agent-creator-skill
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
The skill invokes local scripts to generate an agent; there is no indication of external data exfiltration or harmful code execution.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
80
security
90
transparency
70
maintenance
Findings (1)
Pattern match high
Writes to SKILL.md — self-modifying skill
README.md · prose · downgraded · SKILL.md`, automatically formats the agent ID (e.g., `python_spider_expert`), cr
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.