competitive-intel-brief

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly uses web_search and web_fetch to retrieve public third-party content — e.g., Step 2 fetching GitHub releases.atom feeds and Step 3 fetching full articles from web search results — and then reads and classifies those sources to generate priorities and create/manage intel records, so untrusted external content can materially influence tool actions and decisions.