Caveat verdict

baoyu-danger-gemini-web

18
🔴 Dangerous
High-risk patterns flagged for review — automated deep scan, not behaviorally verified.

The skill uses a reverse-engineered Gemini Web API and executes scripts from an external source, posing a risk of code injection or malicious execution.

⚠ 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.

75
security
100
transparency
90
maintenance

Findings (4)

Pattern match medium

Instructs covert action — may act without user awareness

scripts/gemini-webapi/client.ts · prose · downgraded · silently

Pattern match medium

References child_process — can spawn system processes

scripts/gemini-webapi/utils/paths.ts · prose · downgraded · child_process

Pattern match low

Popular HTTP library — network access

scripts/gemini-webapi/client.ts · prose · downgraded · got

Pattern match low

Opens WebSocket connection

scripts/gemini-webapi/utils/load-browser-cookies.ts · prose · downgraded · WebSocket

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). 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