What security grade does sub-agents-skills have?

sub-agents-skills is graded UNSAFE by AgentSkillsHub's rule-based security scan (SlowMist 11 red-flag categories). Flagged unsafe — do NOT run against real credentials or production data.

Is sub-agents-skills safe to install?

Security audit of shinpr/sub-agents-skills · Codex Skill by shinpr · ★ 59

✕ UNSAFE Basic audit · rule-based scan · SlowMist 11 red-flag categories

No — sub-agents-skills was flagged UNSAFE by AgentSkillsHub's security scan. Do not run it against real credentials or production data.

What it is: Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Cursor, Gemini, or OpenCode from any compatible tool.

Red flags detected (1)

🚩 curl pipe shell

Audit summary

Security grade	✕ UNSAFE
Quality score	76/100
GitHub stars	59
Language	Python
License	MIT
Last updated	2026-07-13

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 Codex Skill audits

Is openclaw safe? — CAUTION · ★ 384.1k
Is hermes-agent safe? — SAFE · ★ 220.6k
Is ui-ux-pro-max-skill safe? — SAFE · ★ 108.6k
Is open-design safe? — SAFE · ★ 81.6k
Is agent-skills safe? — SAFE · ★ 80.4k
Is graphify safe? — SAFE · ★ 77.1k

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 UNSAFE grade is a scan result, not a guarantee — deep 5-dimension audits (code · credentials · vendor · supply-chain · operational) are available for enterprise. Audited: 2026-07-26.