ClawAudit verdict
gpt5-5free
The skill installs a package using npm, which could be a concern if the package is not properly verified.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (2)
References sudo โ requests elevated privileges
skill-card.md ยท prose ยท downgraded ยท sudo
Accesses sensitive environment variables
src/index.js ยท prose ยท downgraded ยท process.env.OPENROUTER_API_KEY
Permissions & capabilities
No declared permissions โ minimal attack surface.
package_install Is this flag fair?
Thanks โ recorded.