Security audit of SalesforceAIResearch/MCP-Universe · MCP Server by SalesforceAIResearch · ★ 592
Use with caution — MCP-Universe triggered warning flags in AgentSkillsHub's security scan. It may be fine for personal trials, but review its credential handling and maintainer before brand or production use.
What it is: MCP-Universe is a comprehensive framework designed for RL training, benchmarking, and developing AI agents for general tool-use.
service persistencesudo usage| Security grade | ⚠ CAUTION |
| Quality score | 69/100 |
| GitHub stars | 592 |
| Language | Python |
| License | Apache-2.0 |
| 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 CAUTION 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.