Security audit of smallcloudai/refact-lsp · Agent Tool by smallcloudai · ★ 68
Yes — refact-lsp 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: Rust executable for Refact Agent, it lives inside your IDE and keeps AST and VecDB indexes up to date, offers agentic tools for an AI model to call. Yes, it works as a LSP server from IDE point of view.
No dangerous patterns were detected: no credential exfiltration, no obfuscated downloads, no sandbox-escape attempts, no prompt-injection markers.
| Security grade | ✓ SAFE |
| Quality score | 70/100 |
| GitHub stars | 68 |
| Language | Rust |
| License | BSD-3-Clause |
| Last updated |
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.