bioservices

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to approximately 40 established bioinformatics services (UniProt, KEGG, ChEMBL, NCBI, etc.) to retrieve biological data and sequences.
  • [EXTERNAL_DOWNLOADS]: The agent is instructed to fetch metadata from arXiv.org (a well-known scientific repository) to generate accurate citations for the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from biological databases and arXiv metadata. While this data ingestion constitutes an indirect prompt injection surface, it is a functional requirement for research analysis and the data sources are reputable scientific institutions.
  • [CREDENTIALS_SAFE]: The skill implements best practices for secret management by using the NCBI_EMAIL environment variable for service identification rather than hardcoding contact information or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:02 AM
Security Audit — agent-trust-hub — bioservices