science-translational-medicine
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to fetch and process data from external websites (AAAS / Science Translational Medicine platform) to ensure guidelines are current. This creates a potential surface for indirect prompt injection if the external content contains instructions designed to manipulate the agent's behavior.
- Ingestion points: External search results and live website content from the AAAS platform.
- Boundary markers: None provided in the instructions to delimit external content from system prompts.
- Capability inventory: Implied use of search or browsing tools to access live URLs.
- Sanitization: No specific sanitization or validation of the external content is requested.
Audit Metadata