bypass

bypass is a command for Claude Code, Cursor from MN-Lizard-Team/aiyu-multi-agent. It costs 0 tokens per session (568 once invoked), scanned A, original, Apache-2.0.

A command for testing whether security controls can be bypassed, including web filters, authentication checks, endpoint detection, debugging protections, and cloud security controls.

In plain words
What is it for?
Use it for authorized security testing of WAFs, authentication systems, EDR tools, anti-debugging measures, and cloud security controls.
Why use it?
It helps identify cases where a security measure does not stop an expected attack technique.

Command for Claude CodeCursor

Written for Claude Code and Cursor: $ARGUMENTS substitution, but also installed under .cursor/.

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.

agentmods
npx agentmods add commands/mn-lizard-team/aiyu-multi-agent/bypass
Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

Made for: Claude Code, Cursor.

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 bypass

README.md
[![agentmods](https://agentmods.dev/badge/commands/mn-lizard-team/aiyu-multi-agent/bypass.svg)](https://agentmods.dev/commands/mn-lizard-team/aiyu-multi-agent/bypass)
Your own site
<a href="https://agentmods.dev/commands/mn-lizard-team/aiyu-multi-agent/bypass"><img src="https://agentmods.dev/badge/commands/mn-lizard-team/aiyu-multi-agent/bypass.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00568
Opus 5 $0.00000 $0.00284
Sonnet 5 $0.00000 $0.00114
Haiku 4.5 $0.00000 $0.00057

Measured 5d ago against content hash 899efdd8ce66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

bypass 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 5d ago.

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.

.cursor/commands/bypass.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bypass

Security control bypass and evasion techniques — WAF bypass, auth bypass, EDR evasion, anti-debug bypass, and cloud security circumvention. Used for testing whether security controls actually hold.


⚠️ CURSOR OUTPUT CONTRACT

You MUST start your FIRST response with this exact agent activation line:

🤖 **Active Agent: `bypass-specialist`** | Skills: `clean-code, red-team-tactics, vulnerability-scanner, bash-linux`

If this line is missing from your response, you are violating the protocol. Add it before any other content.

Required Behavior

  1. Follow the task steps defined below
  2. Apply the Socratic Gate: ask clarifying questions if requirements are unclear
  3. Report completion status at the end

/bypass — Security Control Bypass Testing

$ARGUMENTS


🤖 Agent Activation

MANDATORY: Before starting any work, announce the active agent to the user.

🤖 **Active Agent: `bypass-specialist`** | Skills: `clean-code, red-team-tactics, vulnerability-scanner, bash-linux`

Task

Test whether security controls actually work under adversarial conditions. Every bypass is a finding. Every failed bypass is confidence.

Steps:

  1. Identify the Control

    • What security mechanism is in place?
    • What is it supposed to prevent?
  2. Understand the Mechanism

    • How does it detect/block?
    • What assumptions does it make?
  3. Systematic Bypass Attempt

    • WAF: encoding, case, comments, whitespace, content-type
    • Auth: JWT confusion, OAuth redirect, MFA bypass
    • EDR: in-memory, LOLBins, unhooking, syscalls
    • Anti-debug: patch PEB, hook timing, clear DR
    • Cloud: IMDS, IAM wildcards, misconfigured storage
  4. Document Finding

    • Bypass technique + proof
    • Impact assessment
    • Remediation guidance
  5. Verify Remediation

    • Re-test after fix
    • Check for variant bypasses

Usage Examples

/bypass test WAF on this endpoint
/bypass bypass authentication on this API
/bypass evade EDR detection
/bypass circumvent AppLocker policy
/bypass test cloud IMDS access
/bypass check if anti-debug can be bypassed

Read the full file on GitHub · 91 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. 5d ago First seen · 91 lines · 0 tokens per session scan A 899efdd8ce66

Subscribe to this mod's changes

bypass is a command published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 568 tokens. 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.