uniprot-database
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill interacts exclusively with official UniProt infrastructure at rest.uniprot.org and sparql.uniprot.org. These are well-known and trusted services in the bioinformatics community.
- [SAFE]: All provided code, including the helper script in scripts/uniprot_client.py and examples in references/api_examples.md, uses standard library functions and common packages like requests for legitimate database access.
- [PROMPT_INJECTION]: Evaluated for potential Indirect Prompt Injection (Category 8) due to the ingestion of external data. Ingestion points: Biological annotations and descriptions are fetched via the UniProt REST API. Boundary markers: The skill does not implement explicit markers to separate data from instructions. Capability inventory: The skill has capabilities for network access and local file writing for saving biological data. Sanitization: Data is ingested directly from curated scientific records; given the high reputation and manual review processes of the Swiss-Prot database, the risk is minimal and considered safe.
Audit Metadata