Skills
skills/aminoanalytica/amina-skills/biorxiv-database/Gen Agent Trust Hub

biorxiv-database

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill fetches titles and abstracts from the bioRxiv API, which serves as an indirect prompt injection surface. External paper content could potentially include instructions meant to influence the agent.\n
  • Ingestion points: The _request and find_by_terms methods in scripts/biorxiv_client.py fetch data from api.biorxiv.org.\n
  • Boundary markers: There are no specific delimiters or instructions to ignore potential commands within the retrieved data.\n
  • Capability inventory: The skill allows writing files to the local system (PDFs and JSON results) via the --fetch-pdf and --out command-line options.\n
  • Sanitization: The script does not perform sanitization on the text fields retrieved from the API before returning them to the agent context.\n- [EXTERNAL_DOWNLOADS]: The skill makes network requests to api.biorxiv.org and www.biorxiv.org to retrieve preprint metadata and PDF files. These are well-known and reputable repositories for the life sciences, and the usage is consistent with the skill's intended purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 11:02 PM