swarm-advanced

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

• Third-party content exposure detected (high risk: 0.90). The skill's Research Swarm workflow in SKILL.md explicitly spawns a "Web Researcher" with capabilities like "web-search" and "content-extraction" and runs parallel tasks such as "search recent publications and articles" (mcp__claude-flow__parallel_execute / Phase 1 Information Gathering), which clearly fetches and ingests public/untrusted web and academic content that the agents analyze and use to drive subsequent orchestration and actions.