swarm-advanced

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

• Third-party content exposure detected (high risk: 0.80). The Research Swarm's Phase 1 Information Gathering (mcp__claude-flow__parallel_execute tasks such as "web-search" and "academic-search" and agent capabilities like "web-search" / "content-extraction") instructs agents to fetch and ingest public web articles, datasets, and other third‑party content, exposing the agent to untrusted user-generated or public sources that could carry indirect prompt injection.