unslop-docs

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is to audit and rewrite documentation (README/docs) that are treated as “untrusted input for agents,” meaning the LLM will ingest outsider-authored free text from those docs at runtime (e.g., repo content not authored by the operating user).