# Inkog

> Use this tool when you need to identify and mitigate security vulnerabilities in AI agents and MCP servers before deployment, solving problems like prompt injection and data leakage risks. Inkog scans for flaws and provides compliance reporting aligned with major standards like EU AI Act and NIST AI RMF. It supports integration with 15+ frameworks, making it a versatile solution for securing AI systems.

Canonical page: https://skillsregistry.net/skills/inkog  
JSON: https://api.skillsregistry.net/v1/skills/inkog

## Description

Inkog is an AI security platform that scans AI agents and MCP servers for vulnerabilities before deployment. It detects security flaws like prompt injection, token bombing, infinite recursion, and data leakage risks. The platform supports compliance reporting aligned with EU AI Act, NIST AI RMF, ISO 42001, and OWASP LLM Top 10 standards. Works across 15+ frameworks including LangChain, CrewAI, LangGraph, PydanticAI, n8n, and Flowise.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/inkog)
- **Repository:** <https://github.com/inkog-io/inkog-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": "inkog"
    }
  }
}
```

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