An automated security-testing tool for AI agents. It sends adaptive attacks through an API or web browser to study how a target agent responds.

Use it to run red-team tests against an AI agent through supported transport tools and examine the results.

It helps find whether an AI agent reveals private instructions or internal structure when given carefully adapted prompts. It is intended for academic use only.

red-team — Skill for Claude Code by yechao-zhang

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yechao-zhang/red-team-agent-skills/red-team/github.svg)](https://agentmods.dev/skills/yechao-zhang/red-team-agent-skills/red-team)

Your own site

<a href="https://agentmods.dev/skills/yechao-zhang/red-team-agent-skills/red-team"><img src="https://agentmods.dev/badge/skills/yechao-zhang/red-team-agent-skills/red-team/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yechao-zhang/red-team-agent-skills/red-team"><img src="https://agentmods.dev/badge/skills/yechao-zhang/red-team-agent-skills/red-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,494 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.03494
Opus 5	$0.00024	$0.01747
Sonnet 5	$0.00010	$0.00699
Haiku 4.5	$0.00005	$0.00349

Measured 12d ago against content hash 48ceb2eb92bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

red-team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 14 executable files (scripts/adaptive_attack.py, scripts/analyzer.py, scripts/improved_adaptive_attack.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/red-team/SKILL.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Red Team Agent Skill

Architecture: Hybrid (Python + Native Tools)

Purpose: Extract internal schemas and System Prompts from target AI agents using "nested delegation" (套娃) attack.

System Architecture

The red-team skill orchestrates attacks by delegating communication to specialized transport skills (agent-proxy or dev-browser), which then interact with the target agent.

┌─────────────┐
│ Claude Code │
└──────┬──────┘
       │ 1. Invokes
┌──────▼───────┐
│   red-team   │
│    skill     │
└──────┬───────┘
       │
       │ 2. Selects Transport (via transport.py)
       ▼
┌──────────────┐    ┌─────────────┐
│ agent-proxy  │    │ dev-browser │
│    skill     │    │    skill    │
└──────┬───────┘    └──────┬──────┘
       │                   │
       │ 3. API            │ 3. Browser
       ▼                   ▼
┌─────────────────────────────────┐
│          Target Agent           │
└─────────────────────────────────┘

Hybrid Design

Step	Type	Tool/Method
Read knowledge	Native	Read tool
Initialize attack	Python	AdaptiveNestingAttack class
Get payload	Python	attack.get_current_payload()
Send to target	Hybrid	Transport layer (auto-detect)
Check output file	Native	Read tool
Record attempt	Python	attack.record_attempt()
Judge success	Python	attack.judge_success()
Optimize payload	Native/Python	LLM reasoning or API
Save report	Python	attack.save_report()

Transport Layer (NEW)

The skill now uses a unified transport layer that auto-detects the target type and routes to the appropriate skill:

Target Type	Transport Class	Underlying Skill	Description
Web UI (HTML)	`BrowserTransport`	`dev-browser` OR `playwright-skill`	Direct Browser Control. Handles login, specialized input, and adaptive dual-approval bypass.
REST API	`AgentProxyTransport`	`agent-proxy`	API Gateway. Handles JSON APIs, authentication, and headers.
WebSocket	`WebSocketTransport`	Native Python	Direct WebSocket communication (or via `agent-proxy` for complex protocols).
Gradio	`AgentProxyTransport`	`agent-proxy`	Specialized Gradio client support.

Read the full file on GitHub · 414 lines

Files

What ships with it

39 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 414 lines · 49 tokens per session scan A 48ceb2eb92bb

Subscribe to this mod's changes

red-team is a skill published in the GitHub repository yechao-zhang/red-team-agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 49 tokens to every session and 3,494 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Security

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens