dual-disease-shared-transcriptome-biomarker-research-planner

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill takes user input (disease names and research goals) and uses them to construct a detailed research plan.
  • Ingestion points: User-provided disease pair and shared-biology direction in SKILL.md.
  • Boundary markers: The instructions do not define clear boundaries to separate user input from the agent's internal reasoning.
  • Capability inventory: The skill is limited to text generation and information retrieval; it lacks capabilities for persistent storage, file system modification, or arbitrary shell execution.
  • Sanitization: Input is checked against an 'Out-of-scope' list, but no sanitization of potential instructions embedded within the user input is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 04:46 PM