tooluniverse-sequence-retrieval
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a legitimate interface for bioinformatics research, utilizing specialized tools to query public scientific repositories like NCBI and ENA.
- [SAFE]: The instructions emphasize data quality hierarchy (RefSeq vs GenBank) and proper versioning, which are standard practices for biological data integrity.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external biological databases which could potentially contain untrusted content.
- Ingestion points: Functions such as
NCBI_get_sequenceandena_get_entryretrieve external data into the agent's context (SKILL.md). - Boundary markers: The agent is restricted to a structured 'Sequence Profile Report' format, limiting the interpretation of retrieved data (SKILL.md).
- Capability inventory: Capabilities are confined to searching and fetching biological records via a specific SDK (SKILL.md).
- Sanitization: The workflow focuses on extracting discrete metadata fields like sequence length, topology, and annotation counts rather than executing arbitrary text instructions.
Audit Metadata