Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/akashrpatil/awesome-offensive-security-skillsnpx agentmods add skills/akashrpatil/awesome-offensive-security-skills/amsi-bypassWrote 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/akashrpatil/awesome-offensive-security-skills/amsi-bypass)<a href="https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/amsi-bypass"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/amsi-bypass/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/akashrpatil/awesome-offensive-security-skills/amsi-bypass"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/amsi-bypass.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 | $0.00093 | $0.03946 |
| Opus 5 | $0.00046 | $0.01973 |
| Sonnet 5 | $0.00019 | $0.00789 |
| Haiku 4.5 | $0.00009 | $0.00395 |
Grade A, and why
amsi-bypass 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 8d 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.
This is a copy
100% identical to amsi-bypass — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AMSI Bypass
When to Use
- When operating on a Windows target during a Red Team engagement where PowerShell or .NET memory execution is required, but an EDR/AV is actively inspecting script contents via AMSI.
- To execute tools like Mimikatz, Rubeus, SharpHound, or BloodHound directly in memory without dropping detectable binaries to disk.
- When standard obfuscation fails because AMSI inspects content AFTER deobfuscation at the interpreter level.
- When needing to load custom .NET assemblies via
Assembly.Load()which AMSI intercepts.
When NOT to use: If you need to bypass on-disk AV signature detection, use av-edr-evasion-techniques. For process injection after bypass, use process-hollowing.
Prerequisites
- Administrative or user-level access on a Windows target (AMSI bypass doesn't always require admin)
- PowerShell 5.1+ or PowerShell Core on the target
- Understanding of x86/x64 calling conventions for patching techniques
- For debugging: x64dbg or WinDbg for verifying patches
Workflow
Phase 1: Understanding AMSI Architecture
# Concept: AMSI (Antimalware Scan Interface) is a Windows API that allows applications
# to request AV scans of arbitrary content BEFORE it executes.
# The scan flow:
# 1. User types PowerShell command → PowerShell.exe receives it
# 2. PowerShell calls AmsiScanBuffer() or AmsiScanString() in amsi.dll
# 3. amsi.dll forwards the content to registered AV providers (e.g., Defender)
# 4. AV returns AMSI_RESULT (Clean, Detected, etc.)
# 5. If Detected → PowerShell blocks execution with an error
# Key DLL functions in amsi.dll:
# - AmsiInitialize() → Creates AMSI context for the application
# - AmsiOpenSession() → Opens a scan session
# - AmsiScanBuffer() → Scans raw byte buffer (PRIMARY TARGET)
# - AmsiScanString() → Scans string content
# - AmsiCloseSession() → Closes session
# - AmsiUninitialize() → Destroys AMSI context
# Attack surface: If we corrupt AmsiScanBuffer() or AmsiOpenSession(),
# ALL subsequent scans return "clean" regardless of actual content.
What ships with it
2 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.
- 8d ago First seen · 327 lines · 93 tokens per session scan A b7dd64618e45
amsi-bypass is a skill published in the GitHub repository akashrpatil/awesome-offensive-security-skills (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 3,946 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to amsi-bypass, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
amsi-bypass
Bypass the Windows Antimalware Scan Interface (AMSI) using memory patching, reflection, and obfuscation techniques. Execute undetected PowerShell, VBScript, JScript, and .NET assemblies in-memory without triggering Microsoft Defender or third-party AV/EDR solutions. Use this skill during Red Team engagements when…
cobalt-strike-malleable-c2
Create and implement Malleable C2 profiles in Cobalt Strike to evade network intrusion detection systems (NIDS/IPS) and endpoint detection architectures. This skill focuses on molding the Beacon's HTTP/HTTPS traffic to resemble legitimate network traffic like Amazon, Google, or jQuery.
hunting-for-anomalous-powershell-execution
Hunt for malicious PowerShell activity by analyzing Script Block Logging (Event 4104), Module Logging (Event 4103), and process creation events. The analyst parses Windows Event Log EVTX files to detect obfuscated commands, AMSI bypass attempts, encoded payloads, credential dumping keywords, and suspicious download…
av-edr-evasion-techniques
Bypass antivirus and Endpoint Detection & Response solutions during red team operations using payload obfuscation, process injection, AMSI bypass, ETW patching, and custom loaders. Use this skill when AV/EDR is blocking your payloads, tooling, or post-exploitation activities. Covers shellcode encryption, syscall-based…
certutil-download-execution
Utilize the native Windows binary certutil.exe to download malicious payloads and optionally decode Base64 encoded files as a Living-off-the-Land (LotL) technique. This skill details how attackers bypass application whitelisting and fetch stage-2 implants.
hunting-fileless-and-in-memory-threats
Hunts for fileless and in-memory threats by correlating PowerShell script-block logs, encoded-command usage, in-memory loading patterns, and registry-resident payloads from Windows telemetry. Activates for requests to hunt fileless malware, detect in-memory execution, or find registry-resident and reflective-loading…