NYC

uniprot-database

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The script 'scripts/uniprot_client.py' uses the 'requests' library to communicate with 'https://rest.uniprot.org'. This network activity is necessary for the skill's primary function but targets a domain not included in the predefined whitelist.
  • [PROMPT_INJECTION] (LOW): The skill possesses an indirect prompt injection surface (Category 8) because it ingests and processes data from an external REST API without sanitization.
  • Ingestion points: API responses retrieved from 'https://rest.uniprot.org' within 'scripts/uniprot_client.py'.
  • Boundary markers: None; the agent context is exposed to raw API output without isolation delimiters.
  • Capability inventory: Includes network requests (GET/POST) and data streaming capabilities.
  • Sanitization: No validation or escaping is performed on the protein data or search results before being returned to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:32 PM