SKILLEMALL.ai
GitHub ↗ RU Sign in

CD 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。

zhaoxuya520/reverse-skill Agent Skills author: zhaoxuya520 MIT 4 files body ≈ 1 479 tokens Open the sourcegithub.com↗ analyzed 6 d ago

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…

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureSoftware developmentSecurityPersonal productivitytype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
88/100
safety, quality, tests
Safety 60%
96
Quality 40%
76
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • low Risky intent intent-offensive-security references/telemetry-blinding.md:346
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    然后按 `attack-chain/` 的 initial access 与 lateral movement 章节进入下一阶段。
  • low Risky intent intent-offensive-security SKILL.md:44
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)
    | 内网横向 / AD 攻击 | `pentest-tools/network-attack-defense.md` |
    table
  • low Dangerous commands cmd-execpolicy-bypass SKILL.md:193
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -NoProfile -ExecutionPolicy Bypass -File "<SKILL_ROOT>\skills\scripts\boot…ps1" -Capability @('pe-sieve','sysw…rs3','sysmon') -StartServices
    security skill
  • low Risky intent intent-offensive-security SKILL.md:205
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    - `pentest-tools/network-attack-defense.md` — 内网横向时如何与本 skill 联动
    quoted

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 46/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
  • 100Steps. 42 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1479 tokens
  • 100Running it twice. No mutating operations
  • low 10 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 503: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 42 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.