# shrike

> shrike — cognis-digital-shrike. Use this tool when you need to identify and remediate vulnerabilities in your AI stack, specifically in MCP servers and agent tools. Shrike autonomously detects security flaws and generates fixes, providing a local model for seamless integration. Ideal for AI development and deployment, shrike streamlines security protocols through automated vulnerability assessment and patching, with integration capabilities via git.

Canonical page: https://skillsregistry.net/skills/cognis-digital-shrike  
JSON: https://api.skillsregistry.net/v1/skills/cognis-digital-shrike

## Description

The autonomous security agent for your AI stack — finds the vulns in your MCP servers & agent tools AND writes the fixes, on a local model.

## Trust

- **Trust score (0–1):** 0.83
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/cognis-digital/shrike)

## 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": "cognis-digital-shrike"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-shrike` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-shrike/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