clinical-decision-support

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): No executable scripts or source code were provided in the analyzed files. The skill consists of a README and a clinical example in markdown format.
  • [EXTERNAL_DOWNLOADS] (SAFE): The README references standard scientific Python packages including pandas, numpy, scipy, lifelines, matplotlib, and pyyaml. These are reputable libraries appropriate for the skill's stated purpose.
  • [DATA_EXPOSURE] (SAFE): No credentials, private keys, or sensitive file paths were identified in the documentation or example data.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): The skill defines a surface for processing untrusted clinical data. Ingestion points: User-provided clinical cohorts and biomarker descriptions. Boundary markers: None explicitly defined in the documentation. Capability inventory: Described scripts perform statistical survival analysis and LaTeX-based document generation. Sanitization: None described. This surface is considered safe as it is fundamental to the skill's primary clinical research function.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:59 PM