playbook-creative-ideas

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

• Third-party content exposure detected (medium risk: 0.30). The workflow’s evidence waterfall (Nodes 2–6) ingests externally provided/enrichment text without first selecting a specific item, and that free text is then fed into the single agent call that generates creative_idea_1..3 with verifier evidence assertions.