inter-agent-communication

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md shows the agent performing discovery via directory.lookup and sending HTTP requests to external agents (e.g., posting to "{payment_agent_url}/inbox") and then reading the remote response.status to drive behavior, which clearly ingests untrusted third-party agent content that can influence actions.