build-work-library

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to ingest web text and image references via user-provided inputs or search/fetch actions (references/research-and-media.md, references/data-and-commands.md), which constitutes an active fetch of external sources where arbitrary content can be retrieved.