research-from-vault

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

• Third-party content exposure detected (medium risk: 0.65). This skill’s required workflow can fetch and ingest outsider-authored free text from public web research tools (“browser, web search, YouTube, etc.”) and then “save or summarize the fetched material as vault sources (PDFs or annotated .md companions)”, which the LLM later reads from the vault for synthesis.