tooluniverse-clinical-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and processing data from numerous external medical databases, which presents a surface for indirect prompt injection.
- Ingestion points: External guideline data is retrieved via tools such as NICE_Clinical_Guidelines_Search, PubMed_Guidelines_Search, and GIN_Guidelines_Search, as documented in SKILL.md.
- Boundary markers: The instructions do not include the use of explicit delimiters or protective prompts to prevent the agent from executing instructions potentially hidden within the retrieved guideline text.
- Capability inventory: The skill utilizes multiple search and retrieval tools that perform network operations and requires the agent to synthesize the fetched information into a comprehensive report (SKILL.md).
- Sanitization: There are no instructions for sanitizing, escaping, or validating the content retrieved from external sources before it is incorporated into the agent's response context.
Audit Metadata