multi-agent-architect

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md Step 3 and the Examples) explicitly has agent nodes (e.g., research_node and coding_node) bind tools like web_search, rag_search, and github_tool which ingest public web/GitHub content into state["context"] and are then read by downstream agents, so untrusted third-party content can influence decisions and actions.