github-sensitive-data-cleanup

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via the Layer-4 AI semantic review step, where the agent is instructed to paste flagged commit hashes/file paths/diff excerpts into references/ai_semantic_review_prompt.md; those excerpts originate from the scanned repository’s commit contents (i.e., text authored by others, not chosen by the operating user at runtime).