reactive-comment

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime inputs are the inbound journalist query and optional “recent_context” (e.g., journalist bylines) plus “query_url”; these are outsider-authored free text that the agent would read and potentially include in the LLM context for triage/drafting (e.g., query_text, journalist_bylines).