ClawAudit verdict

github-bounty-finder

45
๐ŸŸ  Risky
Significant concerns โ€” only install if you understand the risks

The skill involves package installation, which could potentially be used maliciously, but its primary purpose seems legitimate.

โš  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.

90
security
60
transparency
80
maintenance

Permission integrity

Installs packages at runtime โ€” transitive dependencies are not auditable

package_install

Findings (2)

Pattern match low

Accesses sensitive environment variables

bin/cli.js ยท prose ยท downgraded ยท process.env.GITHUB_TOKEN

Pattern match low

Popular HTTP library โ€” network access

package.json ยท prose ยท downgraded ยท axios

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

package_install

Is this flag fair?

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