uniprot-protein-database
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches protein metadata, sequences, and annotations from the official UniProt REST API (rest.uniprot.org). This is a well-known scientific service.
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external data (functional annotations, gene names, protein descriptions) that could contain instructions targeting the agent.
- Ingestion points: Data retrieved from the UniProt REST API endpoints (/search, /stream, /idmapping) in SKILL.md.
- Boundary markers: None; the data is directly printed or converted into a DataFrame.
- Capability inventory: Limited to network retrieval and local data processing; no file system writes or arbitrary command execution capabilities are demonstrated.
- Sanitization: The skill does not sanitize or escape the content of the API responses before presenting them to the agent.
Audit Metadata