Security audit of AMAP-ML/LongHorizon-Harness · Codex Skill by AMAP-ML · ★ 803
Yes — LongHorizon-Harness 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 long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
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 | 803 |
| Language | Python |
| License | MIT |
| Last updated |
Browse all Codex Skill skills →
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 130,000+ 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: 2026-08-19.