code-prior-art-survey

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes Procedure 2/3 deep reads of outsider-authored public web content (e.g., READMEs/topic pages/issues/threads from repositories and communities) into LLM context to produce the extracted Markdown artifacts, creating an indirect prompt-injection exposure path.