council

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads external repository issues/PRs and code from GitHub, user/team files from the filesystem, and third-party metrics/scenarios depending on the domain (e.g., via MCP servers like GitHub and Tavily/Brave Search), exposing the agent to outsider-authored free text during intelligence gathering.