# mcp-poisoning-poc

> mcp-poisoning-poc — gensecaihq-mcp-poisoning-poc. Use this tool when you need to demonstrate and test the vulnerability of AI agent workflows to MCP Poisoning Attacks, solving problems related to AI security and robustness. It provides a repository of proof-of-concept attacks, taking in AI workflows as input and outputting vulnerability assessments. Utilize it in contexts where AI security testing and validation are crucial, such as in developing robust AI systems.

Canonical page: https://skillsregistry.net/skills/gensecaihq-mcp-poisoning-poc  
JSON: https://api.skillsregistry.net/v1/skills/gensecaihq-mcp-poisoning-poc

## Description

This repository demonstrates a variety of **MCP Poisoning Attacks** affecting real-world AI agent workflows.

## Trust

- **Trust score (0–1):** 0.56
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/gensecaihq/mcp-poisoning-poc)

## 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": "gensecaihq-mcp-poisoning-poc"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gensecaihq-mcp-poisoning-poc` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gensecaihq-mcp-poisoning-poc/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