scenario-inspiration

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and processes public web references from Are.na, The Met, and Openverse APIs, which ingest outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains HTTP API endpoints for third-party reference sources (Are.na, The Met, Openverse, Cleveland Museum of Art, Wikimedia Commons, and Art Institute of Chicago) in references/sources.md which are queried during runtime content gathering, constituting a common/reputable unofficial operational dependency.