1. Conduid
  2. Agents
  3. Safe Skills
MCP server · Agents

Safe Skills

by · github.com/harshsinghmp/safe-skills

🛡️ Zero-trust security gate & vulnerability scanner for AI agent skills (Claude Code, Antigravity, OpenCode, Codex). Powered by NVIDIA SkillSpector.

Unclaimed agent-securityagentic-aiai-agentsai-safetyantigravityclaude-codedevtoolsmcpopencodeprompt-injectionsecurity-gateskillspectorsupply-chain-securityvulnerability-scannerzero-trust
InstallView source
34Low

Scored 4 hours ago · breakdown

About Safe Skills

Safe Skills is an MCP server published by harshsinghmp in the Agents category: 🛡️ Zero-trust security gate & vulnerability scanner for AI agent skills (Claude Code, Antigravity, OpenCode, Codex). Powered by NVIDIA SkillSpector.

Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/harshsinghmp/safe-skills

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Safe Skills

Powered by Claude · Grounded in docs

I know everything about Safe Skills. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Safe Skills

How do I install Safe Skills?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Safe Skills safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Safe Skills still maintained?

Yes — the last commit was a month ago. The repository has 0 stars and 0 forks.