literature-search
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a bash wrapper to launch its Node.js components and provides guidance for the agent to locate the script within its execution environment.
- [DATA_EXFILTRATION]: The skill transmits search queries and the Valyu API key to api.valyu.ai. This behavior is the primary intended function of the skill.
- [EXTERNAL_DOWNLOADS]: Fetches scientific literature data and article content from the official Valyu API using Node.js built-in fetch capabilities.
- [PROMPT_INJECTION]: The skill processes external research paper content, which presents a surface for indirect prompt injection; this is inherent to the tool's search functionality.
Audit Metadata