federation-status

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow runs a federation status/peers command via a plugin, which at runtime will ingest federation peer data (textual status/peer descriptions) originating from other parties’ federation nodes, making it outsider-authored free text fed into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill runs npx to fetch and execute the npm package @claude-flow/plugin-agent-federation@latest at runtime (seen in "npx -y -p @claude-flow/plugin-agent-federation@latest ruflo-federation ..."), which downloads remote code from the registry and executes it, so it is a runtime external dependency that executes remote code.