ir-playbook

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

• Third-party content exposure detected (high risk: 0.70). The required workflow is a generic incident-response playbook that explicitly expects incident data (e.g., “log entries, email headers, phishing payloads, and command-and-control communications”) to be provided as inputs, which are outsider-authored attacker-controlled free text that the agent would incorporate into its LLM context for analysis.