documents

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

• Third-party content exposure detected (low risk: 0.10). In the required runtime workflow, the agent ingests outsider-authored free text only insofar as it becomes part of a user-supplied content model/brief (e.g., “markdown brief → template fill → render”), and the included scripts/validate-documents.py does not fetch or monitor external text sources.