biorxiv-database
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches preprint metadata and PDF documents from bioRxiv's official API (api.biorxiv.org) and web servers (www.biorxiv.org). These are well-known and reputable scientific resources.
- [COMMAND_EXECUTION]: The provided Python script (scripts/biorxiv_search.py) allows for searching and downloading files via a command-line interface, which is standard functionality for this type of tool.
- [PROMPT_INJECTION]: The skill processes untrusted text content, such as paper titles and abstracts, retrieved from the bioRxiv API.
- Ingestion points: API response content processed in scripts/biorxiv_search.py.
- Boundary markers: Data is structured in JSON format for the agent.
- Capability inventory: Local file writing (results and PDFs) and network access.
- Sanitization: No specific filtering is applied to the retrieved abstract text to remove potentially malicious instructions.
Audit Metadata