hunting-lolbin-abuse-on-windows

hunting-lolbin-abuse-on-windows is a skill for Claude Code, Codex from meltedinhex/analyst-ai-pack. It costs 78 tokens per session (710 once invoked), scanned A, original, Apache-2.0.

A Windows security hunt that finds trusted system tools being used with suspicious arguments to download files or run commands indirectly. It examines process-creation records, such as Sysmon or EDR events.

In plain words
What is it for?
It helps investigate tools such as certutil, mshta, regsvr32, rundll32, bitsadmin, and wmic, then turn confirmed patterns into detection rules.
Why use it?
Legitimate Windows programs can be misused to avoid simple malware detection. This helps separate suspicious use of those programs from their normal presence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps investigate tools such as certutil, mshta, regsvr32, rundll32, bitsadmin, and wmic, then turn confirmed patterns into detection rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/meltedinhex/analyst-ai-pack/hunting-lolbin-abuse-on-windows
Install

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.

Any agent
npx skills add meltedinhex/analyst-ai-pack --skill hunting-lolbin-abuse-on-windows
Clone the repo
git clone --depth 1 https://github.com/meltedinhex/analyst-ai-pack

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for hunting-lolbin-abuse-on-windows

README.md
[![agentmods](https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-lolbin-abuse-on-windows/github.svg)](https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-lolbin-abuse-on-windows)
Your own site
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-lolbin-abuse-on-windows"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-lolbin-abuse-on-windows/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.

agentmods 80×15 button for hunting-lolbin-abuse-on-windows

Your own site · 80×15
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-lolbin-abuse-on-windows"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-lolbin-abuse-on-windows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00710
Opus 5 $0.00039 $0.00355
Sonnet 5 $0.00016 $0.00142
Haiku 4.5 $0.00008 $0.00071

Measured 9d ago against content hash c31b306b8421, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hunting-lolbin-abuse-on-windows 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyst.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/hunting-lolbin-abuse-on-windows/SKILL.md · 88 lines

What it actually says

Hunting LOLBin Abuse on Windows

When to Use

  • You have process-creation telemetry (Sysmon Event ID 1 or EDR process events as CSV/JSON) and want to surface trusted binaries used for malicious proxy execution or download.
  • You are building a detection from known LOLBin argument patterns.

Do not use this as a blocklist of the binaries themselves — they are legitimate. Hunt on the suspicious argument/parent context, not mere presence.

Prerequisites

  • Process-creation events with image path, command line, and (ideally) parent image.

Workflow

Step 1: Score LOLBin invocations

python scripts/analyst.py hunt events.csv

Flags known LOLBins (certutil, mshta, regsvr32, rundll32, bitsadmin, msiexec, installutil, wmic) paired with suspicious arguments (-urlcache, http, javascript:, scrobj, -decode, DownloadString).

Step 2: Add context

Weight by anomalous parent (Office, browser, script host) and unusual execution path.

Step 3: Triage and confirm

Investigate the top-scoring events; confirm whether the download/proxy behavior is legitimate administration or malicious.

Step 4: Operationalize

Convert confirmed patterns into a Sigma rule for ongoing detection.

Validation

  • Flags require a suspicious argument/parent, not just the binary name.
  • Known-benign administrative patterns are distinguishable from abuse in the output.
  • Each flagged technique maps to an ATT&CK ID (T1218.x / T1105).

Pitfalls

  • Alerting on rundll32/regsvr32 presence alone — extremely noisy.
  • Missing renamed LOLBins (hash/signature checks help, name checks do not).
  • Encoded-command obfuscation hiding the true argument intent.

References

Files

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.

Changes

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.

  1. 9d ago First seen · 88 lines · 78 tokens per session scan A c31b306b8421

Subscribe to this mod's changes

hunting-lolbin-abuse-on-windows is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 710 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.

Related

Other skills, from other repositories

sysmon-process-creation-analysis

Analyze Sysmon Event ID 1 (Process Creation) logs to identify malicious executions, living-off-the-land binaries (LOLBins), command-line obfuscation, and suspicious parent-child process relationships.

akashrpatil/awesome-offensive-security-skills · 48 tokens

analyzing-cobalt-strike-beacon-configuration

Extract and analyze Cobalt Strike beacon configuration from PE files and memory dumps to identify C2 infrastructure, malleable profiles, and operator tradecraft.

mukul975/Anthropic-Cybersecurity-Skills · 42 tokens

analyzing-golang-malware-with-ghidra

Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…

mukul975/Anthropic-Cybersecurity-Skills · 95 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…

mukul975/Anthropic-Cybersecurity-Skills · 73 tokens

detecting-dll-sideloading-attacks

Detect DLL side-loading attacks where adversaries place malicious DLLs alongside legitimate applications to hijack execution flow for defense evasion.

adriannoes/awesome-agentic-ai · 36 tokens

hunting-for-registry-run-key-persistence

Use when detect MITRE ATT&CK T1547.001 registry Run key persistence by analyzing Sysmon Event ID 13 logs and registry queries to identify malicious auto-start entries. Use when detecting mitre att&ck t1547.001 registry run key persistence by analyzing.

oyi77/1ai-skills · 66 tokens