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.
npx skills add MingyiSecLab/Mingyi-Atlas --skill ato-methodologygit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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.
[](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/ato-methodology)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/ato-methodology"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/ato-methodology/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.
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/ato-methodology"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/ato-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.01090 |
| Opus 5 | $0.00019 | $0.00545 |
| Sonnet 5 | $0.00008 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
ato-methodology 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 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.
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.
This is a copy
97% identical to ato-methodology — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Account Takeover (ATO) Methodology
ATO is an outcome, not a vuln class. Reach it via 9 canonical paths.
1. Password reset flaws
- Token in URL leaked to Referer (3rd-party CDN, analytics)
- Token guessable (timestamp + user_id, sequential int, predictable RNG)
- Token-no-expiry → reuse forever
- Reset accepts arbitrary email param (mass-assignment style)
- Token not invalidated after password change
- "Forgot username" flows revealing existence
2. Email change without re-auth
POST /api/users/me/email {email: ...} without verifying current password.
Or with verification but verification token leaks.
3. Session fixation
Server accepts attacker-set session cookie. Victim's actions bind to attacker's session.
4. JWT-based ATO
See skills/exploit/web/jwt/SKILL.md — alg confusion, weak secret, kid injection.
5. OAuth-based ATO
See skills/exploit/web/oauth/SKILL.md — redirect_uri bypass + open-redirect chain → code to attacker.
6. IDOR-based ATO
PATCH /api/users/<id>w/o auth check → change victim's email/passwordGET /api/users/<id>/sessions→ harvest victim's session tokens
7. XSS-based ATO
Stored XSS on victim-visible page → exfil cookie / session token to attacker.
8. CSRF on critical state
- CSRF on password change endpoint (no anti-CSRF token)
- CSRF on email change
- CSRF on MFA disable
9. MFA bypass
- TOTP code accepted multiple times w/ short delay (race)
- TOTP code accepted from past N-step (clock skew abuse)
- Backup-code flow doesn't enforce TOTP
- "Trust this device" w/o re-auth on critical action
- Account recovery bypasses MFA entirely
- Phone-number takeover (SIM swap) → SMS 2FA hijack
Chain table
| Primary vuln | Chain partner | Outcome |
|---|---|---|
| Open redirect | OAuth redirect_uri allowlist | OAuth code → attacker → ATO |
| XSS (reflected) | session cookie not HttpOnly | Cookie exfil → ATO |
| XSS (stored) | victim views page | Cookie / session-storage exfil → ATO |
| IDOR on email change | reset flow | Change victim's email, reset, login |
| CSRF on password change | predictable URL | Phishing email triggers password change |
| Predictable reset token | weak RNG audit | Generate victim's token offline → reset |
| OAuth state missing | account linking by email | Attacker pre-creates account, links victim's OAuth → ATO |
| JWT alg=none | server accepts | Mint admin JWT → ATO |
| Email change w/o re-auth + ATO of email | full account graph | Standard playbook for multi-tenant SaaS |
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.
- 9d ago First seen · 105 lines · 39 tokens per session scan A 1461e8d8d390
ato-methodology is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,090 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to ato-methodology, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
web-app-pentest
../../../pentest/web-app-pentest/SKILL.md.
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.12
Ensure access keys are rotated every 90 days or less.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.