dd-unblock-pr

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

• Third-party content exposure detected (high risk: 0.72). The required workflow ingests outsider-authored free text in the form of CI job event/test failure “error message”/logs returned by pup cicd events search/pup cicd tests search and then uses those text snippets as evidence in the agent’s LLM context (indirect prompt-injection risk).