flow-nexus-swarm

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly spawns "researcher" agents with the "web_search" capability and defines Research & Analysis workflows (e.g., "Research machine learning trends...") and GitHub/public template integrations, which implies the agent will fetch and read untrusted public web/social/forum content as part of its workflow.