privileged-access

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

• Third-party content exposure detected (high risk: 0.70). The required workflow only describes assessing PAM by ingesting “PAM configuration and policy data,” “vault metadata,” and “session logs” as untrusted input, which in a real deployment would include outsider-authored free text coming from the external PAM system (vault/recordings/log metadata) into the LLM context.