tooluniverse-expression-data-retrieval

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

• Third-party content exposure detected (high risk: 0.90). The skill programmatically queries and ingests metadata, descriptions, and files from public, user-submitted repositories (ArrayExpress and BioStudies), which the agent reads and interprets to build dataset reports, exposing it to untrusted third-party content.