modelspy
对任意 OpenAI 兼容接口做行为取证，识别背后真正在跑的模型家族与档位。查中转站/API 代理/代充前端有没有偷换便宜模型、验证端点是不是宣称的那个模型、批量抽测降智时使用：六路探针（分词器指纹、陷阱题库、生成速度 TPOT、自我披露、知识截止、Function calling）按权重投票，输出候选排名 + 置信度 + MATCHES/MISMATCH 判定和 HTML 报告。英文场景：identify which LLM actually serves an endpoint, detect reseller model downgrade, verify "is this rea...
Install this skill
or
100/100
Security score
The modelspy skill was audited on Sep 21, 2026. Our scanner tested it across 12 threat categories and found no security issues.
Categories Tested
Security Issues
No security issues detected
This skill passed all security checks.
Scanned on Sep 21, 2026
View Security Dashboard