# Redteam (agent skill)

> Redteam is an agent skill (a SKILL.md file) from agentscope-ai/OpenJudge. Agents load it when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. It works with Claude Code and has 867 GitHub stars.

Use when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success Rate), or "is my app safe to deploy." Outputs ASR paired with over-refusal rate and an audit document. Test your application's safety boundaries systematically.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/agentscope-ai/OpenJudge |
| Skill path | skills/eval_pipeline/07-redteam/SKILL.md |
| Skill name | redteam |
| GitHub stars | 867 |
| Installs on skills.sh | not listed |
| License | Apache-2.0 |
| Skills in repo | 1 |
| Plugin marketplace | no |
| Official | no |
| Works with | Claude Code |
| Category | Security |
| Last commit | Sep 11, 2026 |

## When it triggers

- Use when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming.
- use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success Rate), or "is my app safe to deploy.
- "is my app safe to deploy."

## Add this skill

### Claude Code

```sh
git clone --depth 1 https://github.com/agentscope-ai/OpenJudge.git
cp -r OpenJudge/skills/eval_pipeline/07-redteam ~/.claude/skills/redteam   # personal, or .claude/skills in a project
```

In the Claude apps, zip the skill folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).

### ChatGPT / Codex

```sh
git clone --depth 1 https://github.com/agentscope-ai/OpenJudge.git
cp -r OpenJudge/skills/eval_pipeline/07-redteam .agents/skills/redteam   # repo; ~/.agents/skills for all projects
```

### Cursor

```sh
git clone --depth 1 https://github.com/agentscope-ai/OpenJudge.git
cp -r OpenJudge/skills/eval_pipeline/07-redteam .cursor/skills/redteam   # project; ~/.cursor/skills for all projects
```

Sources (checked 2026-10-07): https://code.claude.com/docs/en/skills, https://support.claude.com/en/articles/12512180-using-skills-in-claude, https://learn.chatgpt.com/docs/build-skills, https://cursor.com/docs/context/skills

---

Canonical page: https://appsgit.com/skills/agentscope-ai-redteam
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed nightly.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.
