Caveat verdict
auto-create-skill
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Skill that extracts workflows from conversations and writes structured SKILL.md files to local agent skill directories; environment detection and file writing are scoped to ~/.claude/skills or equivalent local paths with no exfiltration.
⚠ 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.
100
security
60
transparency
70
maintenance
Permission integrity
Accesses agent memory/configuration files
agent_memory
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.