productatlas-blueprint-creator

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required workflow explicitly instructs the agent to inspect “evidence” sources for existing-system/hybrid work (e.g., bug reports/incidents/support findings and “code paths”), meaning the workflow can ingest outsider-authored free text whenever those evidence inputs come from user-submitted systems the agent is allowed/required to read.