The Agent Skills Directory

[SAFE]: The skill's primary function is to query a model proxy API. A thorough analysis of the instructions and the TypeScript execution script revealed no indicators of prompt injection, obfuscation, or unauthorized access to system resources.
[DATA_EXFILTRATION]: The script performs network requests to 'https://new.fortao.cn' to retrieve model definitions. This behavior is restricted to the skill's stated purpose and does not involve the exfiltration of sensitive local data or credentials.
[CREDENTIALS_UNSAFE]: The skill implements secure credential management by reading the API key from the 'TINY_LLM_PROXY_KEY' environment variable, rather than requiring hardcoded secrets.

model-list