playbook-ai-content-workflow

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

• Third-party content exposure detected (high risk: 0.80). The playbook's Hallucination Management Gate (Section 12) explicitly instructs the agent to "Use web search to find the latest news and resources, and cite your sources," which requires fetching and interpreting open/public web content (third‑party, potentially user‑generated) as a required part of the workflow and thus could allow indirect prompt injection.