pitfall-experience

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads historical capsules, READMEs, and search code from a specific GitHub repository controlled by external contributors without prior item selection, representing an indirect prompt injection risk from repository content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill queries and posts to a specific third-party repository on GitHub (BENZEMA216/openclaw-pitfalls), which constitutes an unofficial external operational dependency on that repository's content and API endpoints.