# AgentShield

> Use this tool when you need to protect AI agents from security threats, such as prompt injection and data exfiltration, with its comprehensive static analysis and real-time runtime interception capabilities. AgentShield solves problems related to AI agent security, including detecting backdoors, tool poisoning, and cross-file attack chains, and provides outputs in the form of alerts and blocked threats. It is ideal for use in environments where AI agents are deployed, particularly when security and reliability are paramount.

Canonical page: https://skillsregistry.net/skills/elliotllliu-agent-shield  
JSON: https://api.skillsregistry.net/v1/skills/elliotllliu-agent-shield

## Description

Full-stack security for AI agents — static analysis + MCP runtime interception. 31 rules detect prompt injection, data exfiltration, backdoors, tool poisoning, and cross-file attack chains. Includes MCP proxy for real-time blocking, Python AST taint tracking, multi-language injection detection (8 languages), and AI-powered deep analysis. Free, offline, zero-config.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-05

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/pottqmzhi9)
- **Repository:** <https://github.com/elliotllliu/agent-shield>

## 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": "elliotllliu-agent-shield"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/elliotllliu-agent-shield` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/elliotllliu-agent-shield/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