provider-fix-documentation

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow can ingest outsider-authored free text via “Aone workitem link / GitLab Code Review link” (and “User-reported documentation errors”), which are then processed by link-info-extractor to extract requirement details that may include arbitrary text from external systems into the agent’s LLM context.