investigate-issue

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

• Third-party content exposure detected (high risk: 0.95). The required workflow is to “Read the body completely” of a GitHub issue and use its text to drive verification and to “Post comment” based on that content; the LLM ingests the outsider-authored issue body (public/third-party contributor text) at runtime via the GitHub issue body.