skill-team-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly gives teammates WebSearch/WebFetch in the Stage 5 "Language Routing Decision" (available_tools = "WebSearch, WebFetch, Read, Grep, Glob") and instructs the lead agent to read and synthesize teammate outputs in Stages 7–8, so public/untrusted web content fetched by teammates can be ingested and materially influence subsequent decisions.