edr-bypass-re

逆向防御方实现 → 红队针对性绕过。把 EDR / Defender / AV 的 hook 表、ETW provider、AMSI 实现先逆向出来，再写针对性的 unhook / 间接 syscall / ETW patch / call stack spoof。对照 MITRE ATT&CK T1562 防御规避。触发关键词：EDR 绕过、AV bypass、免杀、unhook、direct syscall、indirect syscall、Hell's Gate、Halo's Gate、 Tartarus Gate、ETW patch、AMSI patch、call stack spoofing、hardware breakpoint Blindside、MITRE T1562、 ntdll unhook、kernel callback、CrowdStrike 绕过、Defender 绕过、Sentinel One 绕过、Elastic Defend、 Sysmon 规避、PPID spoof、Sleep mask、Process Hollowing、Reflective DLL。

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

70%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Well-structured with a clear sequenced workflow, validation checkpoints, and properly split one-level-deep references. It is let down slightly by some conceptual padding and by deferring executable bypass code to the bundle files instead of showing it inline.

Suggestions

Trim the '核心原理' conceptual diagram and '关键认知' rationale — Claude already understands EDR monitoring surfaces, so keep only the technique-combination guidance.

Inline at least one minimal executable snippet (e.g. an indirect-syscall or AmsiScanBuffer patch skeleton) rather than only pointing to references/unhook-techniques.md, to lift actionability toward copy-paste ready.

Move the product-by-product fingerprint detail fully into references/hook-survey.md and keep SKILL.md to the identification commands, reducing token weight in the overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete tables and code, but includes conceptual framing Claude already knows (e.g. the four-monitoring-surface diagram and '关键认知' rationale paragraphs) that pad the body beyond what a competent model needs.	2 / 3
Actionability	Provides real commands (Get-Service/fltmc filters, pe-sieve invocation, sysmon install) and technique-combination tables, but the in-body implementation guidance is largely '代码骨架见 references/...' with key payloads deferred to bundle files rather than shown copy-paste ready.	2 / 3
Workflow Clarity	A clearly sequenced 6-step workflow (identify EDR → extract hooks → choose bypass combo → implement → sandbox validate → deliver) with an explicit local-sandbox validation checkpoint in Step 5 and a MUST-pass self-check checklist at the end.	3 / 3
Progressive Disclosure	SKILL.md is an overview that signals one-level-deep references — hook-survey.md, unhook-techniques.md, telemetry-blinding.md — all confirmed present in references/, with details correctly split out rather than inlined.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and answers both what it does and when to use it via an explicit trigger-keyword list. It is distinguishable and rich with natural user terms, though somewhat long for a description field.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '把 EDR...hook 表、ETW provider、AMSI 实现先逆向出来，再写针对性的 unhook / 间接 syscall / ETW patch / call stack spoof' — naming specific techniques rather than vague language.	3 / 3
Completeness	Clearly answers 'what' (reverse defender implementations then write targeted bypasses) and 'when' via the explicit '触发关键词' trigger list and MITRE T1562 framing, satisfying both halves.	3 / 3
Trigger Term Quality	A dedicated '触发关键词' clause enumerates natural terms a user would say — 'EDR 绕过、AV bypass、免杀、unhook、direct syscall、ETW patch、AMSI patch、CrowdStrike 绕过、Defender 绕过、Sentinel One 绕过、Elastic Defend、Sysmon 规避' — with broad coverage including product names.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply bounded to EDR/Defender/AV bypass (defender-implementation reverse engineering → targeted evasion), with product-specific and technique-specific triggers unlikely to fire for adjacent skills like generic malware-analysis or attack-chain.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zhaoxuya520/reverse-skill
Path: skills/edr-bypass-re/SKILL.md
Commit: 6aa1362

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.