The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes Python's urllib.request library to perform network operations. These requests are strictly directed to the official KEGG REST API endpoint (https://rest.kegg.jp), which is a reputable service for biological pathway and genomic data.
[DATA_EXFILTRATION]: There is no evidence of the skill attempting to access sensitive local files (such as credentials, SSH keys, or environment variables) or exfiltrating data to unauthorized domains. All network traffic is intended for retrieving academic data.
[PROMPT_INJECTION]: The instructions provided in the skill documentation are focused on guiding the agent to correctly use the KEGG API. No malicious instructions were found that attempt to bypass AI safety guardrails or override system prompts.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute scripts from remote sources. It uses a local Python script (scripts/kegg_api.py) to handle API communication without dynamic code execution patterns like eval() or exec().
[SAFE]: The skill follows best practices for API integration and is intended for legitimate academic use cases in bioinformatics and molecular biology.

kegg-database