ansoff-matrix

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow is to “check session for existing evidence” and then “populate the quadrants” using evidence from other skills/sources (e.g., autonomous-investigation, porters-five-forces, voice-of-customer-miner) and/or runtime research; those workflows commonly fetch or ingest public web content and other parties’ text, which would be read into the LLM context as free-form evidence snippets/URLs.