file-feedback

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow requires searching and reading GitHub issues in celo-org/buy-skill (e.g., lines 163-169), which exposes the agent to outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and executing @celo/buy@0.5.2 from npm via npx, an unpinned remote package identifier that constitutes a weak runtime dependency.