# RAGSHIELD

> Use this tool when you need to detect and prevent corpus poisoning attacks on AI models, solving problems of data integrity and security. RAGSHIELD scans for embedding anomalies and backdoor triggers, providing inputs of suspicious patterns and outputs of alerts and recommendations. It integrates with AI agents through an MCP server, ideal for use in high-stakes applications where model reliability is crucial.

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

## Description

RAG corpus poisoning detector that scans for embedding anomalies and backdoor triggers, with an MCP server for AI agent integration.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/oecbo8kfci)
- **Repository:** <https://github.com/cognis-digital/ragshield>

## 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-ragshield"
    }
  }
}
```

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