embl-ebi-ols
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to the EMBL-EBI Ontology Lookup Service API (https://www.ebi.ac.uk/ols4/api) to fetch ontology data. This is a well-known scientific service and the communication is required for the skill's primary function.
- [COMMAND_EXECUTION]: The skill executes local Python scripts using the
uv runcommand. These scripts are provided within the skill's ownscripts/directory and are used to query the OLS API and process results. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the EBI OLS API, which is an untrusted source that could theoretically contain malicious instructions.
- Ingestion points: Data is fetched from the OLS API in all utility scripts (e.g.,
scripts/get_term.py,scripts/search_ols.py). - Boundary markers: None explicitly used in script outputs; data is returned as structured JSON.
- Capability inventory: The skill has the capability to write to the filesystem via the
--outputparameter and execute provided utility scripts. - Sanitization: The scripts parse the API response as JSON and extract specific fields, providing a level of validation against non-JSON content.
Audit Metadata