kegg-database
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill makes HTTP GET requests to
https://rest.kegg.jpto retrieve genomic and pathway information. This is an interaction with a well-known academic database service. - [PROMPT_INJECTION]: The skill processes data from an external API, creating a surface for potential indirect prompt injection if the source data contains malicious instructions.
- Ingestion points:
scripts/kegg_api.pyusesurllib.request.urlopento fetch data from the KEGG API. - Boundary markers: None; the raw API output is returned directly to the agent without delimitation.
- Capability inventory: The skill is limited to performing network requests to the KEGG domain; however, the agent utilizing it may have broader capabilities.
- Sanitization: None; the retrieved content is decoded and returned as a plain string without filtering or validation.
Audit Metadata