evidence-synthesis-ai
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes clinical evidence and abstracts fetched from external databases like PubMed and Cochrane. This creates a surface where malicious instructions could potentially be embedded in the data being processed by the agent.
- Ingestion points: External medical databases (PubMed, Cochrane CENTRAL, WHO ICTRP).
- Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded prompts in the ingested data.
- Capability inventory: Includes HTTP client functionality for querying databases and parsing structured data (JSON/XML).
- Sanitization: No specific sanitization or validation of the fetched medical content is described to prevent prompt injection.
Audit Metadata