skills/openai/plugins/biorxiv-skill/Gen Agent Trust Hub

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.py to 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_raw and raw_output_path parameters 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 requests library and file system write access via pathlib.
  • Sanitization: The script performs structural validation of the JSON input but does not sanitize the content of the remote response.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 12:21 PM
Security Audit — agent-trust-hub — biorxiv-skill