port-daddy-cli

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and acts on user-generated messages from the Port Daddy pub/sub and inbox APIs (e.g., SKILL.md and references/multi-agent-patterns.md show pd pub, pd sub / GET /msg/:channel, polling and SSE usage and an example where workers "poll" tasks and "Execute assigned task"), meaning untrusted third-party agent messages can be read and used to drive decisions/actions.