kegg-database

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and code examples for accessing the KEGG REST API, a well-known bioinformatics service provided by Kanehisa Laboratories. All network operations target the official API domain (rest.kegg.jp).
  • [EXTERNAL_DOWNLOADS]: The skill suggests installing the requests Python package, which is the standard library for HTTP operations. This is a common and safe dependency for API integration skills.
  • [COMMAND_EXECUTION]: One example demonstrates saving a retrieved PNG image to the local filesystem (pathway.png). This is a standard and expected operation for a biological data retrieval tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API responses (tab-delimited text). While this data is processed by the agent, the risk is minimal as the skill performs structured parsing and does not use the data in sensitive operations like dynamic code execution.
  • Ingestion points: requests.get(url).text in kegg_get and various workflow examples.
  • Boundary markers: None explicitly used for text data, though image data is handled separately.
  • Capability inventory: Writing local image files (pathway.png).
  • Sanitization: Standard string manipulation (strip, split) is used to parse tab-delimited records.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 12:53 AM