write-the-intel-brief

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow described in SKILL.md explicitly requires collecting claims from external sources and attaching archived copies/hashes per claim (via steps like Step 2 and the OSINT-style templates), which necessarily makes the agent ingest outsider-authored free text from the fetched sources at runtime.