llm-wiki-ingestion-stack

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md describes an ingestion workflow that captures and parses outsider-authored “web pages” and “chats/emails” into LLM-ingested extracted text/chunks (capture -> quarantine -> conversion/OCR/ASR -> extraction QA -> source page/wiki draft), with quality checks including “embedded prompt-injection text.”