# IntentProbe

> IntentProbe — mcpware-intentprobe. Use this tool when you need to detect potential security threats in AI models and prevent poisoned servers, skills, and packages from being installed. IntentProbe reads internal activations to identify malicious intent, providing a secure scanning solution for AI agent tooling. It integrates with git, allowing for seamless security checks within development workflows.

Canonical page: https://skillsregistry.net/skills/mcpware-intentprobe  
JSON: https://api.skillsregistry.net/v1/skills/mcpware-intentprobe

## Description

Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.

## Trust

- **Trust score (0–1):** 0.54
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/mcpware/IntentProbe)

## 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": "mcpware-intentprobe"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mcpware-intentprobe` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mcpware-intentprobe/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