Caveat verdict

skill-reviewer

skill-quality-auditor

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

A quality-scoring auditor for AI skills that reads local files and produces structured scorecards; all file operations are local and the workflow is transparent with no network 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.

0
security
90
transparency
70
maintenance

Findings (11)

Pattern match critical

Accesses sensitive system files

references/security.md · code · /etc/passwd

Pattern match high

Pipe to bash — executes piped content as shell commands

references/content-quality.md · prose · downgraded · |bash

Pattern match high

References sudo — requests elevated privileges

references/security.md · code · sudo

Pattern match high

setuid — privilege escalation mechanism

references/security.md · code · setuid

Pattern match high

Accesses .ssh directory

references/security.md · code · .ssh/

Pattern match high

Pipe to sh — executes piped content as shell commands

references/security.md · prose · downgraded · |sh

Pattern match high

Accesses AWS credentials file

references/security.md · prose · downgraded · ~/.aws/credentials

Pattern match medium

References tunneling service

references/security.md · code · ngrok

Pattern match medium

Accesses cloud provider credentials

references/security.md · prose · downgraded · ~/.aws

Pattern match low

Sets world-executable permissions

references/security.md · prose · downgraded · chmod 777

Pattern match low

Base64 encoding/decoding

references/security.md · prose · downgraded · base64-decode

Why the tier is capped

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