The Agent Skills Directory

[DATA_EXFILTRATION] (LOW): The script performs network requests to 'rest.kegg.jp' using urllib.request. This is a non-whitelisted domain, although it is the legitimate endpoint for the skill's purpose. No access to sensitive local files or hardcoded credentials was detected.
[PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface detected. 1. Ingestion points: Raw response data is fetched from the KEGG API in all functions (e.g., kegg_info, kegg_get). 2. Boundary markers: None; the script returns raw string data directly to the agent. 3. Capability inventory: The skill is limited to HTTP GET requests and does not have file system write or command execution capabilities. 4. Sanitization: No sanitization or filtering is performed on the data retrieved from the remote API.

kegg-database