ai-agent-redteam

ai-agent-redteam is a skill for Claude Code from hypnguyen1209/offensive-claude. It costs 55 tokens per session (2,281 once invoked), scanned B, original, MIT.

A security-testing guide for AI agents that use tools, memory, web retrieval, or multi-step planning. It focuses on attacks against the agent’s surrounding workflow, not just the language model.

In plain words
What is it for?
Testing AI assistants, MCP connections, retrieval systems, email or browser agents, and code interpreters for prompt injection, tool abuse, memory poisoning, and excessive permissions.
Why use it?
It helps reveal ways untrusted content, connected tools, or stored memories could steer an agent into unsafe actions. It also supports authorized, repeatable testing of jailbreaks and prompt-injection attacks.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the offensive-claude plugin — 30 skills, 18 commands, 8 agents, 1 hook shipped together

Good fit Testing AI assistants, MCP connections, retrieval systems, email or browser agents, and code interpreters for prompt injection, tool abuse, memory poisoning, and excessive permissions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hypnguyen1209/offensive-claude/ai-agent-redteam
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add hypnguyen1209/offensive-claude --skill ai-agent-redteam
Clone the repo
git clone --depth 1 https://github.com/hypnguyen1209/offensive-claude

Made for: Claude Code.

Or install offensive-claude, the plugin that ships this one along with the rest of its 30 skills, 18 commands, 8 agents, 1 hook.

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.

agentmods badge for ai-agent-redteam

README.md
[![agentmods](https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/ai-agent-redteam/github.svg)](https://agentmods.dev/skills/hypnguyen1209/offensive-claude/ai-agent-redteam)
Your own site
<a href="https://agentmods.dev/skills/hypnguyen1209/offensive-claude/ai-agent-redteam"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/ai-agent-redteam/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.

agentmods 80×15 button for ai-agent-redteam

Your own site · 80×15
<a href="https://agentmods.dev/skills/hypnguyen1209/offensive-claude/ai-agent-redteam"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/ai-agent-redteam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,281 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Server-Side Request Forgery · line 85
    Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.
    Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
  • high Server-Side Request Forgery · line 102
    Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.
    Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.02281
Opus 5 $0.00028 $0.01141
Sonnet 5 $0.00011 $0.00456
Haiku 4.5 $0.00006 $0.00228

Measured 11d ago against content hash 899b65bebdc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

ai-agent-redteam scanned grade B with 1 finding 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 11d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/agency_tool_fuzzer.py, scripts/agent_redteam_harness.py, scripts/indirect_injection_forge.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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

python scripts/agency_tool_fuzzer.py --endpoint $AGENT_URL --tools surface.json --ssrf-canary http://169.254.169.254/

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/ai-agent-redteam/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Red Teaming

Offensive testing of autonomous LLM agents — systems that combine model reasoning with tools, memory, retrieval, and multi-step planning. This is distinct from model-level testing (see ai-security): the attack surface here is the agentic pipeline — untrusted data channels, tool/MCP integrations, persistent memory, and delegated authority. Assumes authorized engagement.

When to Activate

  • Pentesting an LLM agent with tool/function-calling, an MCP client, or a code interpreter
  • Testing RAG / email / browser assistants for indirect or zero-click prompt injection
  • Auditing MCP server integrations for tool poisoning, rug-pull, or line-jumping
  • Assessing persistent memory / long-term context for poisoning and belief drift
  • Evaluating excessive agency: confused-deputy, SSRF/RCE-via-tool, over-privileged actions
  • Running automated jailbreak campaigns (PAIR/TAP/Crescendo/Best-of-N) and measuring ASR
  • Standing up a repeatable PyRIT/Garak/Promptfoo harness mapped to OWASP Agentic Top 10 / ATLAS

Technique Map

Technique ATT&CK CWE Reference Script
Indirect / zero-click prompt injection (EchoLeak-class) T1566.002 / AML.T0051.001 CWE-1427 references/indirect-prompt-injection.md scripts/indirect_injection_forge.py
RAG corpus poisoning & markdown/image exfiltration T1567 / AML.T0070 CWE-1426 references/indirect-prompt-injection.md scripts/indirect_injection_forge.py
Browser-agent hijack (Comet/CometJacking, Atlas) T1071.001 / AML.T0051 CWE-1427 references/indirect-prompt-injection.md scripts/indirect_injection_forge.py
MCP tool poisoning / line-jumping T1059 / AML.T0053 CWE-1427 references/mcp-tool-poisoning.md scripts/mcp_tool_poison_server.py
MCP rug-pull (silent redefinition) T1554 / AML.T0010 CWE-494 references/mcp-tool-poisoning.md scripts/mcp_tool_poison_server.py
Persistent memory poisoning (MINJA/MemoryGraft) T1565.001 / AML.T0070 CWE-349 references/memory-context-poisoning.md scripts/memory_poison_minja.py
Excessive agency / confused-deputy tool abuse T1548 / AML.T0053 CWE-862 references/excessive-agency-tool-abuse.md scripts/agency_tool_fuzzer.py
Tool output → SSRF / RCE chaining T1059 / AML.T0054 CWE-918 / CWE-94 references/excessive-agency-tool-abuse.md scripts/agency_tool_fuzzer.py
Automated multi-turn jailbreak (Crescendo/TAP/PAIR) AML.T0054 / AML.T0071 CWE-1426 references/automated-jailbreak-multiturn.md scripts/multiturn_jailbreak.py
Best-of-N / encoding obfuscation jailbreak AML.T0054 CWE-1426 references/automated-jailbreak-multiturn.md scripts/multiturn_jailbreak.py
Harness & ASR scoring (PyRIT/Garak/Promptfoo) AML.T0071 CWE-1426 references/agent-redteam-tooling.md scripts/agent_redteam_harness.py

Read the full file on GitHub · 113 lines

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.

  1. 11d ago First seen · 113 lines · 55 tokens per session scan B 899b65bebdc3

Subscribe to this mod's changes

ai-agent-redteam is a skill published in the GitHub repository hypnguyen1209/offensive-claude (357 stars, last pushed 25d ago), licensed MIT. It adds 55 tokens to every session and 2,281 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

bt6-queue-audit

Audit the full pull-request and issue queue of a BT6 research or support repository, classifying readiness, evidence risk, and next action without mutating tracker state.

elder-plinius/T3MP3ST · 40 tokens

bt6-issue-steward

Triage and steward issues in BT6 research and support repositories, deciding whether to answer, reproduce, correct evidence, link work, design a feature, route security, implement, or close.

elder-plinius/T3MP3ST · 46 tokens

bt6-merge-train

Run an explicitly authorized, conservative BT6 merge train that processes validated pull requests one at a time and reconciles repository, CI, evidence, and issue state after each merge.

elder-plinius/T3MP3ST · 42 tokens

bt6-pr-audit

Audit one pull request in a BT6 research or support repository at an exact head SHA, covering correctness, research integrity, security, tests, contracts, and merge readiness.

elder-plinius/T3MP3ST · 40 tokens

bt6-provider-review

Audit an external AI/API provider and its integration into a BT6 repository for service reality, independent verification, trust boundaries, secret handling, API/model correctness, completeness, claim traceability, and merge readiness.

elder-plinius/T3MP3ST · 46 tokens

xiaohongshu-search-full

Search Xiaohongshu (XHS / RedNote) notes by keyword with full field extraction including body text, topics/tags, image list URLs, video stream URL, publish timestamp, and all engagement stats (likes, collects, comments, shares). Supports all page filter options: sort order (general, latest, most liked, most commented…

browser-act/skills · 254 tokens