biorxiv-skill
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Network Request Capability: The skill uses
scripts/rest_request.pyto fetch data from the bioRxiv and medRxiv APIs. While the instructions guide the agent toward these specific services, the script itself is a flexible REST client capable of connecting to any URL provided in the input. - File System Operations: The skill supports saving raw API responses to the local file system. The
save_rawandraw_output_pathparameters allow for data to be written to a user-defined location, which is a standard feature for this type of tool but involves direct file system interaction. - Indirect Prompt Injection Surface: The skill ingests data from external sources for summarization.
- Ingestion points: Content is retrieved from external URLs via
scripts/rest_request.py. - Boundary markers: No specific delimiters or 'ignore' instructions are used when presenting fetched data to the agent.
- Capability inventory: Includes network access via the
requestslibrary and file system write access viapathlib. - Sanitization: The script performs structural validation of the JSON input but does not sanitize the content of the remote response.
Audit Metadata