# Shrike Security

> Use this tool when you need to protect AI agents from security threats, such as prompt injection and SQL injection attacks. It solves problems related to data breaches and unauthorized access by detecting vulnerabilities and isolating sensitive information like PII. With threat intelligence capabilities, it provides actionable outputs to secure AI systems, taking input from various sources to identify potential risks.

Canonical page: https://skillsregistry.net/skills/io-github-shrike-security-shrike-mcp  
JSON: https://api.skillsregistry.net/v1/skills/io-github-shrike-security-shrike-mcp

## Description

AI agent security scanner — prompt injection detection, SQL injection, PII isolation, threat intel.

## Trust

- **Trust score (0–1):** 0.85
- **Verification tier:** scanned

## Facts

- **Version:** 1.1.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-06-16

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.Shrike-Security%2Fshrike-mcp)
- **Repository:** <https://github.com/Shrike-Security/shrike-mcp>

## 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": "io-github-shrike-security-shrike-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-shrike-security-shrike-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-shrike-security-shrike-mcp/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