beamer

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs using Membrane actions and proxy requests (e.g., list-posts, get-post, list-comments and membrane request CONNECTION_ID /path/to/endpoint) to fetch Beamer posts/comments and arbitrary API responses, which are user-generated/untrusted third-party content the agent would read and which could influence subsequent actions.