cross-linker

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

• Third-party content exposure detected (medium risk: 0.30). The skill reads and LLM-processes the contents of user-controlled vault markdown pages (Step 2 “Read the full content” and Step 5 “Collect outgoing links” from misc pages), meaning outsider-authored free text present in those files is ingested at runtime for link extraction.