tooluniverse-expression-data-retrieval
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes metadata from external biological repositories, creating a surface where instructions embedded in external content could potentially influence the agent.
- Ingestion points: Data is ingested through tools including
arrayexpress_search_experiments,biostudies_search,geo_search_datasets, andPubMed_search_articles(SKILL.md). - Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore potential commands embedded in study titles or descriptions when generating reports (SKILL.md).
- Capability inventory: The agent can search repositories, retrieve experiment metadata, and extract data download links for biological datasets (SKILL.md, examples.md).
- Sanitization: There is no evidence of specific filtering, validation, or sanitization applied to the retrieved text before it is presented to the user or processed by the agent.
Audit Metadata