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 yara-huntinggit 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/yara-hunting)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/yara-hunting"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/yara-hunting/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/yara-hunting"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/yara-hunting.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 | $0.01668 |
| Opus 5 | $0.00039 | $0.00834 |
| Sonnet 5 | $0.00015 | $0.00334 |
| Haiku 4.5 | $0.00008 | $0.00167 |
Grade B, and why
yara-hunting 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 https://mb-api.abuse.ch/api/v1/ -X POST -d 'query=get_yara&yara_rule=YourRule' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://mb-api.abuse.ch/api/v1/ -X POST -d 'query=get_yara&yara_rule=YourRule' How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YARA Rule Authoring + Hunting
Anatomy of a good rule
import "pe"
import "hash"
rule MalFamily_DropperVariant_Q4_2024 {
meta:
author = "you"
date = "2024-11-20"
description = "MalFamily dropper, observed Q4 2024 campaign"
hash = "deadbeefdeadbeefdeadbeefdeadbeef"
tlp = "amber"
confidence = "high"
false_positives = "low (test against AV vendor samples)"
mitre = "T1055"
strings:
$magic = { 4D 5A 90 00 03 } // MZ + DOS header
$config_marker = { 7A 89 ?? ?? 4F 8C } // 6-byte signature, 2 wildcards
$string1 = "loader_stage_2" wide
$string2 = "cmd.exe /c " ascii
$api1 = "VirtualAllocEx"
$api2 = "WriteProcessMemory"
$api3 = "CreateRemoteThread"
// Avoid generic strings — they cause FPs.
condition:
uint16(0) == 0x5A4D and // PE header
filesize < 5MB and // bounded — avoids huge-file scans
$config_marker and // unique marker
2 of ($api1, $api2, $api3) and // at least 2 of the 3 process-inject APIs
any of ($string*) and
pe.imports("ws2_32.dll", "WSAStartup") and // network capability
not pe.is_signed // unsigned
}
The condition tools you need
// Filesize / offset reads (no module)
filesize > 100KB and filesize < 5MB
uint32(0x3c) > 0 and uint32(uint32(0x3c)) == 0x4550 // valid PE
// "for" loops over offsets / sections
for any i in (0..pe.number_of_sections - 1):
(pe.sections[i].name == ".text" and pe.sections[i].entropy > 7.0)
// "of"
1 of them // any one string
all of ($a*) // all $a*-prefix strings
3 of ($s1, $s2, $s3, $s4, $s5) // at least 3 of 5
// Hash module
hash.sha256(0, filesize) == "..." // exact-match rule
hash.imphash() == "..." // PE import hash (fragile but high-signal)
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 · 171 lines · 77 tokens per session scan B 144d49db262d
yara-hunting 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 1,668 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). 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.