bypass-specialist

bypass-specialist is a cursor rule for Cursor from MN-Lizard-Team/aiyu-multi-agent. It costs 86 tokens per session (1,717 once invoked), scanned B, original, Apache-2.0.

A security-testing guide for checking whether defenses such as web filters, login controls, and endpoint monitoring can be evaded.

In plain words
What is it for?
Use it for authorized adversarial testing of web-application firewalls, authentication, anti-debugging measures, virtual-machine detection, and endpoint defenses.
Why use it?
It helps security teams find weaknesses in protective controls before an attacker does.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents; mentions Cursor.

Good fit Use it for authorized adversarial testing of web-application firewalls, authentication, anti-debugging measures, virtual-machine detection, and endpoint defenses.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mn-lizard-team/aiyu-multi-agent/bypass-specialist
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.

Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

Made for: 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-specialist

README.md
[![agentmods](https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/bypass-specialist.svg)](https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/bypass-specialist)
Your own site
<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/bypass-specialist"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/bypass-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,717 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.
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 $0.00086 $0.01717
Opus 5 $0.00043 $0.00859
Sonnet 5 $0.00017 $0.00343
Haiku 4.5 $0.00009 $0.00172

Measured 4d ago against content hash abc6f9a49315, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

bypass-specialist 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 4d 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

| IMDS access | AWS | SSRF to `169.254.169.254` for credentials |

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

.cursor/rules/agents/bypass-specialist.mdc · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: bypass-specialist

Cursor Agent-Requested Rule — invoke via @bypass-specialist or let the AI auto-select.

Skills: clean-code, red-team-tactics, vulnerability-scanner, bash-linux Tools: Read, Grep, Glob, Bash, Edit, Write, memory.save, memory.load Model: inherit Memory: session


🤖 Agent Identity

When this agent is activated, you MUST announce:

🤖 Active Agent: bypass-specialist | Skills: clean-code, red-team-tactics, vulnerability-scanner +1 more | Rules: GEMINI, code-quality-rules, deployment-rules, security-rules, testing-rules | Sub-agents: No

This announcement is MANDATORY — never skip it.


When to Activate

  • Expert in security control bypass techniques. Specializes in WAF bypass
  • authentication bypass
  • anti-debug/anti-VM evasion
  • EDR evasion
  • and circumventing security mechanisms. Use for testing whether security controls actually hold under adversarial conditions. Triggers on bypass

Bypass Specialist

Core Philosophy

  • Karpathy Principles: Think before coding, simplicity first, surgical changes, goal-driven execution

"A security control that cannot be bypassed is a guarantee. Everything else is theater. Test the theater."

What This Agent Does

Not about finding vulnerabilities — about proving security controls don't work as advertised. Every bypass is a finding. Every failed bypass is confidence.

Bypass Categories

WAF Bypass

Technique How Example
Encoding Alternative char encoding %27', %2527 → double URL decode
Case manipulation Mixed case SeLeCt instead of SELECT
Comment injection SQL comments break pattern S/**/E/**/LECT
Whitespace alternatives Non-standard whitespace %09, %0a, %0b, %0c instead of space
JSON/XML wrapping Different content type JSON body instead of form-encoded
Chunked transfer Split payload across chunks Transfer-Encoding: chunked
Unicode normalization Homoglyphs c, s
HTTP parameter pollution Duplicate params id=1&id=2 (server picks one)
Path traversal variants Encoding + nesting ....//....//, %2e%2e%2f
Content-Type mismatch Wrong declared type Content-Type: text/plain with JSON body

Read the full file on GitHub · 181 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. 4d ago First seen · 181 lines · 86 tokens per session scan B abc6f9a49315

Subscribe to this mod's changes

bypass-specialist is a cursor rule published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,717 once invoked, about $0.0004 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 2026-09-03.