uniprot-database

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill interacts with the official UniProt REST API at rest.uniprot.org to retrieve protein data. This is a well-known scientific resource and the communication is conducted through standard HTTPS requests.\n- [SAFE]: The provided Python script scripts/uniprot_client.py implements basic data retrieval and ID mapping functions without any evidence of malicious behavior, obfuscation, or unauthorized access to the local system.\n- [PROMPT_INJECTION]: The skill processes data from an external source which represents an indirect prompt injection surface.\n
  • Ingestion points: The client fetches protein data and annotations from rest.uniprot.org within the search_proteins, get_protein, and stream_results functions in scripts/uniprot_client.py.\n
  • Boundary markers: No specific delimiters or instructions are used to separate retrieved data from the agent's instructions.\n
  • Capability inventory: The skill's functionality is limited to performing network requests and returning data; it does not possess capabilities for file modification, system command execution, or other high-risk operations.\n
  • Sanitization: No sanitization is performed on the retrieved biological data, though the risk is minimal given the specialized nature of the content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:48 PM