tooluniverse-pathway-disease-genetics
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill explicitly instructs the agent to "write and run Python code via Bash" for computation, statistics, and data processing tasks. This provides the agent with a mechanism to execute generated code on the underlying system.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by ingesting data from untrusted external biological databases and using that data to drive computational analysis.
- Ingestion points: The skill utilizes tools to fetch data from the GWAS Catalog, OpenTargets, GTEx, Reactome, and STRING.
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions within the biological data retrieved.
- Capability inventory: The agent is empowered to perform file-write operations and execute shell commands (via Bash) to run Python scripts.
- Sanitization: There is no requirement in the instructions to sanitize or validate the content of the external data before it is processed or interpolated into code.
Audit Metadata