audit-data-exposure

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

• Third-party content exposure detected (medium risk: 0.30). The workflow’s required runtime (scripts/scan_repository_data_exposure.py) ingests and scans readably LLM-processed repository file contents and Git history/blobs from the target repo provided by the user (including commit messages and tag messages), so an outsider who can author/push content into that repo can cause poison text to be scanned without any prerequisite selection of a specific item.