bootstrap-agents-md

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

• Third-party content exposure detected (high risk: 0.70). The required workflow reads the target repo’s existing human-authored docs (e.g., README/AGENTS/CONTRIBUTING/docs) during Phase 0 evidence gathering and injects their free-text into the agent’s LLM context; these are outsider-authored if the operating user did not author/choose that text.