researcher

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

• Third-party content exposure detected (high risk: 1.00). The skill's Research Process (Phase 2 steps 4–5) and Critical Rules (1 & 3) explicitly require using WebSearch and WebFetch to search for and fetch full public webpages—including community discussions, blogs, and Stack Overflow—so the agent reads and acts on untrusted third-party content that can influence its decisions.