mfa-bypass

mfa-bypass is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 49 tokens per session (1,768 once invoked), scanned A, original, Apache-2.0.

A security testing guide for weaknesses in multi-factor authentication, also called 2FA, which asks for a second proof such as a one-time code.

In plain words
What is it for?
Use it to review OTP verification, backup codes, remembered devices, password resets, and other flows that should require 2FA.
Why use it?
It helps find login and account-recovery paths where the second check can be skipped, reused, guessed, or bypassed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to review OTP verification, backup codes, remembered devices, password resets, and other flows that should require 2FA.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/mfa-bypass
About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,497 stars · on GitHub · decepticon.red

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 PurpleAILAB/Decepticon --skill mfa-bypass
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

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.

agentmods badge for mfa-bypass

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/mfa-bypass/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/mfa-bypass)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/mfa-bypass"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/mfa-bypass/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 mfa-bypass

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/mfa-bypass"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/mfa-bypass.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 1,768 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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: 3 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 YARA Match · line 120
    YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
    Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
  • medium Data Exfiltration · line 27
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 75
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00049 $0.01768
Opus 5 $0.00024 $0.00884
Sonnet 5 $0.00010 $0.00354
Haiku 4.5 $0.00005 $0.00177

Measured 9d ago against content hash f5a1e85ca022, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mfa-bypass scanned grade A 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w "%{http_code} $p\n" "https://<TARGET>$p"
packages/decepticon/decepticon/skills/standard/exploit/web/mfa-bypass/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MFA / 2FA Bypass Playbook

Logic flaws in the second factor are pure ATO. Common because devs ship the happy path (enter code → success) and forget the negative paths: response tampering, brute force, replay, race, alternate flows, remembered devices.

1. Detection — map the 2FA surface

Enumerate every flow that should require a second factor:

# 1. Inventory paths involved in step-up
for p in /login /login/2fa /api/2fa/verify /mfa/verify /account/security \
         /account/email /account/password /password/reset /password/reset/confirm \
         /oauth/authorize /api/session /api/session/elevate /backup-codes; do
  curl -s -o /dev/null -w "%{http_code}  $p\n" "https://<TARGET>$p"
done

# 2. Submit a wrong OTP — what does the response look like?
curl -s -i -X POST "https://<TARGET>/api/2fa/verify" \
  -H 'Content-Type: application/json' -H "Cookie: session=<HALF_AUTHED>" \
  -d '{"code":"000000"}'

# 3. Rate-limit probe — burst 20 wrong codes
for i in $(seq 1 20); do
  printf '%s ' "$(curl -s -o /dev/null -w '%{http_code}' -X POST \
    "https://<TARGET>/api/2fa/verify" -H 'Content-Type: application/json' \
    -H "Cookie: session=<HALF_AUTHED>" -d "{\"code\":\"$(printf '%06d' $i)\"}")"
done; echo
# If no 429 / lockout → brute force is open

2. Flaw matrix

Class Symptom Bypass
Response manipulation server returns {"success":false} but client trusts it intercept → flip to true
Status-code tamper 401 vs 200 only checked client-side rewrite 401 → 200 in proxy
Flag tamper mfa_required=true in JWT/JSON edit to false, resign / unsigned alg
No rate limit unlimited wrong OTPs 6-digit OTP = 10⁶ — brute over hours
Per-IP limit only limit on attacker IP, not on user rotate IPs / X-Forwarded-For
OTP reuse same code valid after use replay last code in a new session
OTP no expiry code from yesterday still works mine old SMS / email
Predictable OTP seeded by userid/timestamp precompute
Backup-code abuse unlimited tries, codes never expire / not invalidated brute backup codes endpoint
Race condition two requests in flight — both succeed parallel POSTs (HTTP/2 single-packet attack)
Missing 2FA on flow /login enforces, /api/login does not use alternate endpoint
Missing 2FA on password change password change re-enables full session reset → skip 2FA
Password reset skips 2FA reset token logs you in without 2FA abuse reset link
OAuth / SSO skips 2FA social login returns a fully-authed session login via Google instead
Remember-me cookie persistent cookie skips 2FA forever steal remember-me via XSS / log leak
Direct object access /api/account works on half-authed session call protected APIs pre-2FA
Enrollment race attacker enrolls own TOTP for victim before victim does hit /2fa/enroll first post-login
Recovery channel takeover SMS → SIM swap, email → email ATO downstream factor compromise

Read the full file on GitHub · 138 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. 9d ago First seen · 138 lines · 49 tokens per session scan A f5a1e85ca022

Subscribe to this mod's changes

mfa-bypass is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,497 stars, last pushed 13d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,768 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.