browser-research-agent
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a benign workflow for data gathering and citation. It focuses on recording source URLs, dates, and claims without involving executable code or system modifications.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and source code from reputable entities (OpenAI, Nous Research). These references are used for informational purposes and do not trigger unauthorized installations or remote script executions.
- [PROMPT_INJECTION]: The skill is designed to process external web data, which introduces a surface for indirect prompt injection. However, the workflow lacks exploitable capabilities like file system writes or shell execution that could be leveraged by such an injection.
Audit Metadata