tooluniverse-bioinformatics-resource-discovery
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a discovery resource, providing the agent with systematic ways to query established bioinformatics repositories. All listed external sources (bio.tools, ELIXIR, Bioconductor, CRAN) are official, well-known entities in the scientific community.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by ingesting untrusted data from external registries into the agent's context.
- Ingestion points: Data is retrieved from external APIs via tools such as
BioTools_search,SmartAPI_search_apis,ELIXIRTeSS_search_materials,Bioconductor_search_packages, andCRAN_get_package(all withinSKILL.md). - Boundary markers: None are explicitly defined in the instructions to separate external data from agent instructions.
- Capability inventory: The skill primarily lists discovery and metadata retrieval tools. It mentions the ability to call found APIs directly or use
tooluniverse-create-toolfor wrapping, which suggests a path to network operations based on discovered data. - Sanitization: No explicit sanitization or validation of the retrieved registry content is described in the markdown instructions.
Audit Metadata