Caveat verdict

filechat-rag

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill reads Google Drive files and uses API keys, potentially exposing private documents to cloud services.

⚠ 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.

53
security
70
transparency
80
maintenance

Findings (4)

Pattern match high

Possible hardcoded credential

tests/setup.js · prose · downgraded · API_KEY: 'AIzaSyAOx5NDLxsyRjd0qWT33LXZ_KKwMtyzOe4

Pattern match medium

Possible prompt injection — attempts to redefine agent identity

SKILL.md · prose · downgraded · you are now

Pattern match medium

References child_process — can spawn system processes

sync-all.js · prose · downgraded · child_process

Pattern match low

Accesses sensitive environment variables

image_parse.js · prose · downgraded · process.env.GEMINI_API_KEY

Why the tier is capped

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

Permissions & capabilities

Requires 3 system binaries. (1 elevated: npm).

file_write

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API