ontology-term-resolution
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill makes network requests to well-known scientific data providers to fetch ontology metadata. These include the European Bioinformatics Institute (ebi.ac.uk) for OLS4 and ZOOMA services, as well as Bioregistry.io and Identifiers.org. These operations are essential for the skill's primary purpose and target official, public API endpoints.
- [INDIRECT_PROMPT_INJECTION]: The skill processes free-text input and metadata files which could potentially contain instructions aimed at the agent.
- Ingestion points: The scripts
resolve_terms.py,validate_terms.py,map_terms.py, andlookup_prefix.pyaccept data via command-line arguments and file inputs via the--inputflag. - Boundary markers: The instructions do not define specific delimiters for separating user-provided data from agent instructions.
- Capability inventory: The skill includes the ability to write to the file system (via the
-ooutput flag in scripts) and perform network requests to scientific APIs. - Sanitization: The scripts perform standard URL encoding of input parameters for API safety, though they do not implement specific natural language sanitization for agent instructions.
Audit Metadata