Caveat verdict

scientific-drawing

scientific-drawing-skill-1-0-0

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

The skill requires installation of multiple packages and access to the Gemini API or OpenRouter API, which could be considered risky if not properly vetted.

⚠ 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.

80
security
40
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Permissions & capabilities

No declared permissions — minimal attack surface.

package_installcredential_accessnetwork_in

Is this flag fair?

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