# agentshield

> agentshield — aiconnai-agentshield. Use this tool when you need to protect AI agent tools and MCP servers from security threats, such as command injection and secret theft. Agentshield provides a security firewall that detects and fixes vulnerabilities in under 50ms, with a 100% offline Rust SAST and 1-click auto-fix capabilities. Ideal for use with popular AI models like Claude, GPT, and Gemini, agentshield ensures secure operation through its SARIF-compatible interface.

Canonical page: https://skillsregistry.net/skills/aiconnai-agentshield  
JSON: https://api.skillsregistry.net/v1/skills/aiconnai-agentshield

## Description

🛡️ The security firewall for AI agent tools & MCP servers (Claude 5, GPT-5.6, Gemini 3.8, Antigravity, Cursor, Codex, Hermes). Catch command injection, secret theft & toxic flows in <50ms. 100% offline Rust SAST + 1-click auto-fix + SARIF.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-25

## Source

- **Source listing:** [GitHub](https://github.com/aiconnai/agentshield)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "aiconnai-agentshield"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/aiconnai-agentshield` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/aiconnai-agentshield/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt