Caveat verdict

git-repo

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

Git repository management skill for SourceGit integration with ghq; allowed-tools are explicitly declared (Read, Edit, Write, Bash restricted to git/ghq/mv/ls) and the workflow matches standard git repo management.

⚠ 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.

45
security
70
transparency
70
maintenance

Findings (5)

Pattern match high

References SSH/GPG private keys

SKILL.md · frontmatter · ssh-key

Pattern match high

Accesses .ssh directory

ssh-key.md · code · .ssh/

Pattern match medium

Instructs covert action — may act without user awareness

scripts/repo-to-bare-worktree.sh · prose · downgraded · Silently

Pattern match low

References agent configuration files

move-worktree.md · prose · downgraded · CLAUDE.md

Pattern match low

References agent memory files

worktree.md · prose · downgraded · MEMORY.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/C/F). 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