Caveat verdict

claudify

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

This is a meta-skill that helps convert functionality into Claude Code automation types (agents, skills, rules, hooks); it uses only Read/Write/Edit/Glob/Skill/Bash(mkdir) tools for local file creation and has no network access or data 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.

58
security
70
transparency
70
maintenance

Findings (3)

Pattern match critical

Pipe to sh — executes piped content as shell commands

resources/hook-examples.md · code · |sh

Pattern match medium

References agent configuration files

resources/rules-guide.md · code · CLAUDE.md

Pattern match low

References agent memory files

persist.md · prose · downgraded · MEMORY.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

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