Is MTPLX safe to install?

Security audit of youssofal/MTPLX · Claude Skill by youssofal · ★ 2.7k

✓ SAFE Basic audit · rule-based scan · 42 published rules

Yes — MTPLX 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: The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

No dangerous patterns were detected: no credential exfiltration, no obfuscated downloads, no sandbox-escape attempts, no prompt-injection markers.

Audit summary

Security grade	✓ SAFE
Quality score	63/100
GitHub stars	2.7k
Language	Python
License	Apache-2.0
Last updated	2026-11-07

Check before you install

What credentials does it ask for, and where are they stored?
Is the maintainer identifiable and the repo actively maintained?
Read the install scripts and network calls before trusting it.

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

Related Claude Skill audits

Is skills safe? — SAFE · ★ 184.5k
Is claude-code safe? — SAFE · ★ 154.8k
Is claude-mem safe? — SAFE · ★ 114.4k
Is archify safe? — SAFE · ★ 94.4k
Is Understand-Anything safe? — SAFE · ★ 91.1k
Is career-ops safe? — SAFE · ★ 80.9k

Browse all Claude Skill skills →

This is AgentSkillsHub's free basic audit: an automated rule-based scan with 42 published rules built on SlowMist's agent-security taxonomy (credential theft, obfuscated payloads, privilege escalation, covert instructions to the agent, and more) across 186,000+ 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: 2026-11-07.