hap-mcp-app-builder

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

• Third-party content exposure detected (low risk: 0.10). The workflow executes a script (scan_apps.py) that performs an HTTP request to GitHub (raw.githubusercontent.com) to check for updates, fetching external release metadata and notes, which constitutes a low-risk indirect prompt injection vector.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains an update check script that fetches and executes remote content from an external GitHub repository (mingdaocom/hap-skills) during runtime, which constitutes an operational dependency with common reputable unofficial provenance.