open-researcher-guide
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the open_researcher Python package and the OpenResearcher project maintained by the GAIR-NLP research group. These references are documented for functionality and originate from a well-known research entity.
- [PROMPT_INJECTION]: The skill facilitates the ingestion of academic literature from external sources like arXiv and OpenAlex. This creates a surface for indirect prompt injection, common in research automation tools. 1. Ingestion points: Research papers are retrieved from OpenAlex and arXiv backends (SKILL.md). 2. Boundary markers: Explicit delimiters for external content are not shown in the provided code snippets. 3. Capability inventory: The pipeline performs network operations for search and writes research reports to the local file system (SKILL.md). 4. Sanitization: No specific sanitization or filtering of retrieved paper content is described in the examples.
Audit Metadata