uniprot-database
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- PROMPT_INJECTION (LOW): Indirect Prompt Injection Surface identified.
- Ingestion points: Data enters the agent context from the UniProt REST API (
rest.uniprot.org) as specified in the search and retrieval endpoints. - Boundary markers: No explicit delimiters or 'ignore instructions' directives are mentioned for handling the API responses.
- Capability inventory: The skill is designed for bioinformatics workflows and Python script execution (referencing
uniprot_client.py), where the agent may take actions based on protein sequence or annotation data. - Sanitization: No sanitization, validation, or escaping of the content returned by the API (FASTA, JSON, TSV) is documented.
- EXTERNAL_DOWNLOADS (SAFE): The skill connects to
rest.uniprot.orgto fetch protein data. While this domain is not on the pre-approved whitelist, it is the official source for the UniProt database and its use is strictly aligned with the skill's primary scientific purpose.
Audit Metadata