Security audit of osaurus-ai/osaurus · MCP Server by osaurus-ai · ★ 6.6k
Use with caution — osaurus 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: Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
agent memory thefttunnel service| Security grade | ⚠ CAUTION |
| Quality score | 70/100 |
| GitHub stars | 6.6k |
| Language | Swift |
| License | MIT |
| 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.