Is mint-bench safe to install?

Security audit of xingyaoww/mint-bench · Agent Tool by xingyaoww · ★ 133

✓ SAFE Basic audit · rule-based scan · SlowMist 11 red-flag categories

Yes — mint-bench passed AgentSkillsHub's rule-based security scan with no dangerous patterns detected. As with any third-party skill, confirm what credentials it requests before production use.

What it is: Official Repo for ICLR 2024 paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang*, Zihan Wang*, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng and Heng Ji.

Red flags detected (1)

Audit summary

Security grade✓ SAFE
Quality score67/100
GitHub stars133
LanguagePython
LicenseApache-2.0
Last updated

Check before you install

Run a live scan → Full details & install 5-dimension deep audit

This is AgentSkillsHub's free basic audit: an automated rule-based scan covering SlowMist's 11 red-flag categories (credential exfiltration, obfuscated payloads, sandbox escape, prompt injection, and more) across 117,000+ open-source AI agent skills and MCP servers, refreshed every 8 hours. A SAFE grade is a scan result, not a guarantee — deep 5-dimension audits (code · credentials · vendor · supply-chain · operational) are available for enterprise. Audited: 2026-07-03.