uniprot-database

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates communication with the official UniProt REST API (rest.uniprot.org) for protein sequence retrieval, ID mapping, and functional annotation searches. This is a well-known and established scientific service provider.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data in the form of protein records and annotations which are incorporated into the agent's context.
  • Ingestion points: API responses from rest.uniprot.org search and retrieval endpoints.
  • Boundary markers: The instructions do not explicitly define delimiters for external data in the provided query examples.
  • Capability inventory: The skill focus is on data retrieval and analysis; no dangerous operations such as arbitrary command execution, local file system writes, or persistence mechanisms are identified.
  • Sanitization: No explicit sanitization or filtering of API response content is described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:37 PM
Security Audit — agent-trust-hub — uniprot-database