maple-onboard

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads companion skills from a GitHub repository via HTTPS when they are not installed locally, which is fetching outsider-accessible repository files.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external GitHub URL for reading companion files at runtime if not installed locally, representing an unofficial repository dependency with weak provenance.