drug-discovery-search
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a shell script (
scripts/search) and a Node.js CLI (scripts/search.mjs) to perform search operations. It includes a helper command to resolve the script path within the agent's plugin environment. - [SAFE]: The skill communicates exclusively with the official vendor-controlled API (
api.valyu.ai) and implements standard practices for API key storage in the user's home directory. - [PROMPT_INJECTION]: The skill processes data from external drug discovery databases, creating a surface for indirect prompt injection which is handled as structured data.
- Ingestion points: Data is fetched from
api.valyu.aiand returned to the agent context viascripts/search.mjs. - Boundary markers: Absent. Search results are returned as raw JSON objects.
- Capability inventory: The skill has the capability to write to its configuration file and perform network requests to the vendor API.
- Sanitization: Absent. External content is not sanitized before being returned to the agent context.
Audit Metadata