# agent-immune

> agent-immune — denial-web-agent-immune. Use this tool when you need to protect AI agents from potential threats and enhance their security. The agent-immune tool provides adaptive threat intelligence, scanning outputs and limiting rates to prevent attacks, and hardening prompts to ensure secure interactions. It is ideal for use cases requiring robust AI agent security, such as multi-turn conversations and sensitive data processing.

Canonical page: https://skillsregistry.net/skills/denial-web-agent-immune  
JSON: https://api.skillsregistry.net/v1/skills/denial-web-agent-immune

## Description

Adaptive threat intelligence for AI agent security — semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/denial-web/agent-immune)

## 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": "denial-web-agent-immune"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/denial-web-agent-immune` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/denial-web-agent-immune/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