CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

69

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

68%Weight 40%Scale 1-5

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

The body is well-structured and actionable with concrete commands and a clear workflow, supported by real reference files for progressive disclosure. The main weakness is the absence of an explicit validation feedback loop in a destructive/risky-operation workflow, capping workflow clarity.

Suggestions

Add an explicit validate→fix→retry loop after Step 5 (e.g., 'if Defender/Sysmon alerts fire, identify the source, adjust the technique combination, and re-run') to lift workflow clarity above the destructive-operation cap.

Inline a minimal code skeleton in Step 4 or ensure references/unhook-techniques.md is directly linked from that step so the implementation step is self-contained.

Resolve the dangling bootstrap path: create scripts/bootstrap-reverse.ps1 or remove the bootstrap command so progressive disclosure references are all real.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence (no basic EDR/PDF-style concept explanations), with a tight core-principle diagram and command blocks, but has minor padding in the legal statement and routing prose that could be trimmed. It sits above the 'mostly efficient' anchor but not at fully lean.

4 / 5

Actionability

Provides concrete executable PowerShell (Get-Service filter, pe-sieve invocation, sysmon install) and a technique-selection table, but Step 4 delegates code to references rather than inlining it, leaving minor gaps. Mostly executable guidance.

4 / 5

Workflow Clarity

A clear 6-step sequence exists with a sandbox validation checkpoint in Step 5, but for destructive/risky EDR operations there is no explicit validate→fix→retry feedback loop, which caps the score at 3 per the destructive-operation guidance.

3 / 5

Progressive Disclosure

Content is well split across three real one-level-deep reference files (hook-survey.md, unhook-techniques.md, telemetry-blinding.md) with a dedicated 参考资料 section, but the bootstrap references a scripts/bootstrap-reverse.ps1 that does not exist and uses a placeholder <SKILL_ROOT> path, leaving minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 highly specific, third-person, and explicitly covers both what the skill does and when it should trigger, with a rich keyword list for routing. It is among the strongest descriptions in the reference set.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—'unhook / 间接 syscall / ETW patch / call stack spoof'—covering the four EDR monitoring surfaces comprehensively, matching the anchor for listing several specific concrete actions.

5 / 5

Completeness

Clearly states what it does ('逆向防御方实现 → 红队针对性绕过') and when to use it via the concrete trigger keyword list, explicitly answering both what and when.

5 / 5

Trigger Term Quality

An explicit '触发关键词' block provides comprehensive natural terms including synonyms and product names ('EDR 绕过', 'unhook', 'Hell's Gate', 'Tartarus Gate', 'Defender 绕过', 'ntdll unhook'), matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (EDR-only bypass tied to MITRE T1562) with distinct triggers and explicit scope separation from sibling skills, giving minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.