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 malware-triagegit 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/malware-triage)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/malware-triage"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/malware-triage/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/malware-triage"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/malware-triage.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 | $0.00084 | $0.01606 |
| Opus 5 | $0.00042 | $0.00803 |
| Sonnet 5 | $0.00017 | $0.00321 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
malware-triage 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Malware Triage — 15 minute first verdict
You have a suspicious binary. Goal: in 15 minutes, decide CLEAN / SUSPICIOUS / MALICIOUS / NEEDS-DEEPER.
Phase 1: Static (5 min)
# 1. File format
file sample.bin
exiftool sample.bin # author / compile timestamp / version
# 2. Hash + reputation
sha256sum sample.bin
# Submit to: VirusTotal, MalwareBazaar, IntelX, Joe Sandbox, ANY.RUN
# Often the verdict already exists — saves you 14 minutes.
# 3. Strings — fast triage signal
strings -n 8 sample.bin | sort -u | head -100
strings -e l -n 8 sample.bin | sort -u | head -50 # wide (UTF-16) strings on Windows
# Suspicious strings to grep for:
strings sample.bin | grep -iE 'http|https|wmic|powershell|cmd.exe|temp|appdata|amsi|defender|reflectiveloader'
# 4. Format-specific: PE
peresearcher sample.exe # OR python pefile
python3 -c '
import pefile
p = pefile.PE("sample.exe")
print("Compile time:", p.FILE_HEADER.TimeDateStamp)
print("Sections:", [(s.Name.decode().rstrip("\x00"), s.SizeOfRawData, s.get_entropy()) for s in p.sections])
print("Imports:", [(e.dll.decode(), [i.name.decode() if i.name else hex(i.ordinal) for i in e.imports]) for e in p.DIRECTORY_ENTRY_IMPORT])
'
# 5. Entropy → packed?
python3 -c '
import math
data = open("sample.bin","rb").read()
counts = [data.count(bytes([b])) for b in range(256)]
total = len(data)
ent = -sum((c/total)*math.log2(c/total) for c in counts if c)
print(f"Entropy: {ent:.3f} / 8 — {'packed' if ent > 7.5 else 'normal'}")
'
# 6. YARA against canonical rulesets
yara -r /opt/yara-rules/ sample.bin
yara -r /opt/Neo23x0-signature-base/ sample.bin
Phase 2: Dynamic (5 min — in an isolated VM)
# Pre-flight (do this once, save snapshot)
# - Disconnected network OR use INetSim/FakeNet-NG to fake services
# - Procmon recording (Process / File / Network / Registry filters)
# - Wireshark capturing on the snapshot's network adapter
# - Fakedns / inetsim listening for DNS / HTTP / SMTP / FTP
# Detonate
cp sample.bin C:\tmp\sample.exe
# Right-click → Run as admin OR sample.exe in cmd
# Observe for 60-180 seconds, then take snapshot
# Then revert VM for next run
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 · 143 lines · 84 tokens per session scan A 4adc2543cdf6
malware-triage is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,606 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. 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-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.
cis-aws-foundations-6.1.2
Ensure CIFS access is restricted to trusted networks to prevent unauthorized access.
cis-aws-foundations-2.3
Ensure security contact information is registered.