open-targets-search
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill facilitates the collection and storage of a Valyu API key. The instructions guide the agent to request the key from the user and save it using a setup command. Network communication is directed to the official API endpoint at
api.valyu.ai. - [COMMAND_EXECUTION]: The skill utilizes local shell and Node.js scripts (
scripts/search,scripts/search.mjs) to perform its primary function. It includes a helper command usingfindto resolve the script path within the environment, which is a standard procedure for locating installed resources. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest search results from an external data source (Open Targets). This creates a standard surface for indirect prompt injection, but the skill follows typical tool patterns and does not exhibit specific vulnerabilities beyond the inherent risk of processing external content.
Audit Metadata