uniprot-database
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves protein sequences and annotations from the official UniProt REST API.
- Evidence: The
scripts/uniprot_client.pyandreferences/api_examples.mdfiles use thehttps://rest.uniprot.orgdomain for searching and retrieving biological data. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the UniProt API, which enters the agent's context.
- Ingestion points: Data ingestion occurs through network requests to the UniProt API as implemented in
scripts/uniprot_client.pyand demonstrated inreferences/api_examples.md. - Boundary markers: No explicit delimiters or instructions are used to distinguish the retrieved external data from the agent's own instructions.
- Capability inventory: The skill possesses network access for API interactions and provides documented examples for local file system writes.
- Sanitization: The skill does not perform validation or sanitization of the external content before it is processed.
Audit Metadata