clinical-cohort-protocol-designer
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and reference modules. No executable scripts, subprocess calls, or system-altering commands were identified in the SKILL.md or the associated references.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided research questions. Ingestion points: Clinical research queries provided by the user. Boundary markers: Explicit scope definitions and mandatory output structure (Sections A-L) mitigate the impact of malicious content in prompts. Capability inventory: Text generation only; no tool use or external network capabilities are configured. Sanitization: Input is validated through a set of follow-up questions to ensure the request fits within the cohort design scope.
Audit Metadata