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 xs-leaksgit 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/xs-leaks)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/xs-leaks"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/xs-leaks/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/xs-leaks"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/xs-leaks.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 | $0.00033 | $0.01005 |
| Opus 5 | $0.00016 | $0.00502 |
| Sonnet 5 | $0.00007 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
xs-leaks 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 8d 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.
try { await fetch(url, {mode:'no-cors', credentials:'include'}); } catch {} This is a copy
98% identical to xs-leaks — 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XS-Leaks (Cross-Site Leaks)
XS-Leaks abuse browser primitives that leak information ACROSS origins. Attacker page can observe whether a cross-origin GET returned different content based on victim's authenticated state. Smaller than full cross-origin read (which is blocked), but enough to enumerate identifiers, detect membership, learn search-result presence.
1. Categories
1.1 Timing oracles
Cross-origin fetch / image load timing varies by server response size. Attacker measures load time → infers content.
const start = performance.now();
const img = new Image();
img.onerror = () => console.log(performance.now() - start);
img.src = 'https://target.com/api/users/me/notifications';
1.2 Frame counting (window.frames.length)
Some pages embed N iframes when authenticated and 0 when not. Attacker
iframes target page and reads iframe.contentWindow.frames.length.
1.3 Window name / postMessage leak
iframe.contentWindow.name is preserved across navigation. Some pages
set it w/ user-identifying data.
1.4 Error-event oracle
<img src=target.com/api/user/{id}/data> triggers different onerror
behavior based on response code (403 vs 404 vs 200 w/ image content-type).
1.5 CSS injection style oracle
<link rel=stylesheet href=target.com/page> — different applied styles
leak state via getComputedStyle of attacker page.
1.6 Search result presence
Many search endpoints return cached/non-cached headers indicating hits. Attacker measures cache hit vs miss timing for guessed search terms.
1.7 ID guessability (XS-Search)
for (const guessed_id of guessable_set) {
const url = `https://target.com/api/user/${guessed_id}`;
// measure timing or frame-count differential
}
2. xsleaks.dev — canonical reference
Full taxonomy + browser-version compatibility matrix: https://xsleaks.dev/
Atlas agents should consult this for current technique viability — browser mitigations evolve fast (COOP, COEP, Cross-Origin-Opener-Policy).
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.
- 8d ago First seen · 119 lines · 33 tokens per session scan A ee1ab8b07579
xs-leaks is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,005 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 98% identical to xs-leaks, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
web-enumeration
../../../red-team/web-enumeration/SKILL.md.
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-2.5
Ensure MFA is enabled for the 'root' user account.
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.