tooluniverse-immunotherapy-response-prediction
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a comprehensive clinical workflow using verified parameters for professional bioinformatics and medical tools such as OpenTargets, FDA, PubMed, and cBioPortal. All external interactions are directed at well-known scientific and governmental services.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests patient-specific data including cancer types and mutation lists. While this constitutes an attack surface for indirect prompt injection, the instructions emphasize normalization and structured parsing of this data before querying scientific databases, effectively mitigating the risk of instructions embedded in the clinical data being executed by the agent.
Audit Metadata