HackSkills is an organized knowledge base of installable skills that gives AI agents practical security knowledge across areas such as web security, privilege escalation, reverse engineering, and digital forensics. It is intended for bug bounty work, penetration testing, CTF competitions, and authorized security research. The catalogue entries are the project's own master, category, and topic skills.
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 yaklang/hack-skills --skill windows-av-evasiongit clone --depth 1 https://github.com/yaklang/hack-skillsWrote 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/yaklang/hack-skills/windows-av-evasion)<a href="https://agentmods.dev/skills/yaklang/hack-skills/windows-av-evasion"><img src="https://agentmods.dev/badge/skills/yaklang/hack-skills/windows-av-evasion/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/yaklang/hack-skills/windows-av-evasion"><img src="https://agentmods.dev/badge/skills/yaklang/hack-skills/windows-av-evasion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket fail
- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 2 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 YARA Match · line 17 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high YARA Match · line 112 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00049 | $0.03166 |
| Opus 5 | $0.00024 | $0.01583 |
| Sonnet 5 | $0.00010 | $0.00633 |
| Haiku 4.5 | $0.00005 | $0.00317 |
Grade A, and why
windows-av-evasion 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 5d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- windows-av-evasion — 100% identical, 0 lines differ
- windows-av-evasion — 100% identical, 0 lines differ
- windows-av-evasion — 95% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: AV/EDR Evasion — Expert Attack Playbook
AI LOAD INSTRUCTION: Expert AV/EDR evasion techniques for Windows. Covers AMSI bypass, ETW bypass, .NET assembly loading, shellcode execution, process injection, unhooking, payload encryption, and signature evasion. Base models miss detection-specific bypass chains and syscall-level evasion nuances.
0. RELATED ROUTING
Before going deep, consider loading:
- windows-privilege-escalation when privesc tools are blocked by AV
- windows-lateral-movement when lateral movement tools trigger EDR
- active-directory-kerberos-attacks when Rubeus/Mimikatz are detected
- active-directory-acl-abuse for non-binary AD attacks (less AV-sensitive)
Advanced Reference
Also load AMSI_BYPASS_TECHNIQUES.md when you need:
- Detailed AMSI bypass code patterns (memory patching, reflection)
- PowerShell-specific AMSI bypasses
- .NET AMSI bypass techniques
1. AMSI BYPASS OVERVIEW
AMSI (Antimalware Scan Interface) inspects PowerShell, .NET, VBScript, JScript, and Office macros at runtime.
Key AMSI Bypass Categories
| Category | Method | Detection Risk | Persistence |
|---|---|---|---|
| Memory patching | Patch AmsiScanBuffer in amsi.dll |
Medium | Per-process |
| Reflection | Modify AMSI init flags via .NET reflection | Medium | Per-session |
| String obfuscation | Encode/split AMSI trigger strings | Low | Per-payload |
| PowerShell downgrade | Force PS v2 (no AMSI) | Low | Per-session |
| CLM bypass | Escape Constrained Language Mode | Medium | Per-session |
| COM hijack | Redirect AMSI COM server | Low | Per-user |
Quick AMSI Bypass (One-Liners)
# PowerShell v2 downgrade (if .NET 2.0 available — no AMSI in v2)
powershell -Version 2
# Reflection-based (set amsiInitFailed = true)
# Obfuscated to avoid static detection — see AMSI_BYPASS_TECHNIQUES.md for full patterns
What ships with it
1 file 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.
- 5d ago First seen · 343 lines · 49 tokens per session scan A 86506b6e5bf2
windows-av-evasion is a skill published in the GitHub repository yaklang/hack-skills (2,133 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 3,166 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…