biomedical-search
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the
findcommand to locate its internalsearchscript within the platform's plugin cache and subsequently execute it with user-supplied arguments. - [EXTERNAL_DOWNLOADS]: The skill connects to the external domain
api.valyu.aito retrieve biomedical research data. This network activity is fundamental to the skill's search functionality and is clearly documented. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted full-text content from various external biomedical databases.
- Ingestion points: Data is ingested via the output of the
scripts/searchcommand from the Valyu API. - Boundary markers: No explicit delimiters or boundary instructions are provided in the skill text to separate untrusted data from agent instructions.
- Capability inventory: The skill possesses the capability to execute local scripts and perform network operations.
- Sanitization: No evidence of content sanitization or filtering was found in the provided instructions.
Audit Metadata