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 adriannoes/awesome-agentic-ai --skill performing-threat-hunting-with-yara-rulesgit clone --depth 1 https://github.com/adriannoes/awesome-agentic-aiWrote 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/adriannoes/awesome-agentic-ai/performing-threat-hunting-with-yara-rules)<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/performing-threat-hunting-with-yara-rules"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/performing-threat-hunting-with-yara-rules/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/adriannoes/awesome-agentic-ai/performing-threat-hunting-with-yara-rules"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/performing-threat-hunting-with-yara-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 68 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high System Prompt Leakage · line 430 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Privilege Escalation · line 68 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00053 | $0.03236 |
| Opus 5 | $0.00026 | $0.01618 |
| Sonnet 5 | $0.00011 | $0.00647 |
| Haiku 4.5 | $0.00005 | $0.00324 |
Grade A, and why
performing-threat-hunting-with-yara-rules 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 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt update && sudo apt install -y yara Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performing Threat Hunting with YARA Rules
Scan files, directories, and memory dumps using YARA rules to identify malware families, suspicious patterns, and IOC matches.
When to Use
- Proactively hunting for unknown malware variants across network shares, endpoints, and email attachments
- Scanning quarantine directories or sandbox outputs for malware family classification
- Searching process memory dumps for injected code or in-memory-only payloads
- Validating threat intelligence IOCs against a large corpus of collected samples
- Triaging incident response artifacts to identify known malware families quickly
- Building automated detection pipelines that scan new files on ingestion
Do not use for real-time endpoint protection (use EDR agents instead); YARA scanning is best suited for batch hunting, triage, and post-collection analysis where scan latency is acceptable.
Prerequisites
- YARA 4.x installed (
apt install yaraon Debian/Ubuntu,brew install yaraon macOS) - Python 3.8+ with
yara-python(pip install yara-python) yarGenfor automated rule generation (git clone https://github.com/Neo23x0/yarGen)- Sample malware corpus or suspicious files for scanning (from malware zoos, VT, or incident artifacts)
- Optional:
pefilefor PE header analysis,malduckfor memory carving - Threat intel YARA rule sets (e.g., YARA-Rules community repository, Florian Roth signature-base)
Workflow
Step 1: Install YARA and Python Bindings
# Linux
sudo apt update && sudo apt install -y yara
# Python bindings
pip install yara-python
# Verify installation
yara --version
python3 -c "import yara; print(yara.YARA_VERSION)"
Step 2: Write a Basic YARA Rule
Create rules that match on strings, hex patterns, and file metadata:
// File: rules/emotet_loader.yar
rule Emotet_Loader_2026 {
meta:
author = "Threat Intel Team"
description = "Detects Emotet first-stage loader DLL"
date = "2026-01-20"
reference = "https://attack.mitre.org/software/S0367/"
mitre_attack = "T1059.001, T1055.001"
severity = "critical"
strings:
// Emotet export function name patterns
$export1 = "DllRegisterServer" ascii
$export2 = "RunDLL" ascii nocase
// Obfuscated string decryption routine
$decrypt_loop = { 8B 45 ?? 33 45 ?? 89 45 ?? 8B 4D ?? 03 4D ?? }
// PowerShell download cradle in embedded script
$ps_cradle = /powershell[^\n]{0,50}-e(nc|ncodedcommand)/i
// Known C2 URI patterns
$uri1 = "/wp-content/uploads/" ascii
$uri2 = "/wp-admin/css/" ascii
$uri3 = "/wp-includes/" ascii
// PE characteristics
$mz = "MZ" at 0
condition:
$mz and
filesize < 2MB and
(
($export1 and $decrypt_loop) or
($ps_cradle and any of ($uri*)) or
(2 of ($uri*) and $decrypt_loop)
)
}
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 434 lines · 53 tokens per session scan A 11e3834b50eb
performing-threat-hunting-with-yara-rules is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 14d ago), licensed MIT. It adds 53 tokens to every session and 3,236 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
importing-a-codebase
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).
starting-a-new-project
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.