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 killvxk/cybersecurity-skills-zh --skill analyzing-malware-persistence-with-autorunsgit clone --depth 1 https://github.com/killvxk/cybersecurity-skills-zhWrote 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/killvxk/cybersecurity-skills-zh/analyzing-malware-persistence-with-autoruns)<a href="https://agentmods.dev/skills/killvxk/cybersecurity-skills-zh/analyzing-malware-persistence-with-autoruns"><img src="https://agentmods.dev/badge/skills/killvxk/cybersecurity-skills-zh/analyzing-malware-persistence-with-autoruns/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/killvxk/cybersecurity-skills-zh/analyzing-malware-persistence-with-autoruns"><img src="https://agentmods.dev/badge/skills/killvxk/cybersecurity-skills-zh/analyzing-malware-persistence-with-autoruns.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 | $0.00053 | $0.00998 |
| Opus 5 | $0.00026 | $0.00499 |
| Sonnet 5 | $0.00011 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
analyzing-malware-persistence-with-autoruns scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(cmd, capture_output=True, text=True, timeout=600) How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用 Autoruns 分析恶意软件持久化
概述
Sysinternals Autoruns 从 Windows 上的数百个自动启动扩展点(ASEP)提取数据,扫描 18 个以上类别,包括 Run/RunOnce 键、服务、计划任务、驱动程序、Winlogon 条目、LSA 提供程序、打印监视器、WMI 订阅和 AppInit DLL。数字签名验证过滤 Microsoft 签名条目。比较功能通过基线差异识别新增的持久化机制。VirusTotal 集成检查哈希信誉。通过 -z 标志进行离线分析,支持取证磁盘镜像检查。
前置条件
- Sysinternals Autoruns(GUI)和 Autorunsc(CLI)
- 目标系统上的管理员权限
- Python 3.9+,用于自动化分析
- VirusTotal API 密钥,用于信誉检查
- 干净的基线导出,用于比对
操作步骤
步骤 1:自动化持久化扫描
#!/usr/bin/env python3
"""自动化基于 Autoruns 的持久化分析。"""
import subprocess
import csv
import json
import sys
def scan_and_analyze(autorunsc_path="autorunsc64.exe", csv_path="scan.csv"):
cmd = [autorunsc_path, "-a", "*", "-c", "-h", "-s", "-nobanner", "*"]
result = subprocess.run(cmd, capture_output=True, text=True, timeout=600)
with open(csv_path, 'w') as f:
f.write(result.stdout)
return parse_and_flag(csv_path)
def parse_and_flag(csv_path):
suspicious = []
with open(csv_path, 'r', errors='replace') as f:
for row in csv.DictReader(f):
reasons = []
signer = row.get("Signer", "")
if not signer or signer == "(Not verified)":
reasons.append("未签名的二进制文件")
if not row.get("Description") and not row.get("Company"):
reasons.append("缺少元数据")
path = row.get("Image Path", "").lower()
for sp in ["\temp\\", "\appdata\local\temp", "\users\public\\"]:
if sp in path:
reasons.append(f"可疑路径")
launch = row.get("Launch String", "").lower()
for kw in ["powershell", "cmd /c", "wscript", "mshta", "regsvr32"]:
if kw in launch:
reasons.append(f"LOLBin:{kw}")
if reasons:
row["reasons"] = reasons
suspicious.append(row)
return suspicious
if __name__ == "__main__":
if len(sys.argv) > 1:
results = parse_and_flag(sys.argv[1])
print(f"[!] {len(results)} 个可疑条目")
for r in results:
print(f" {r.get('Entry','')} - {r.get('Image Path','')}")
for reason in r.get('reasons', []):
print(f" - {reason}")
What ships with it
6 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.
- 11d ago First seen · 93 lines · 53 tokens per session scan A 02b8bcac989d
analyzing-malware-persistence-with-autoruns is a skill published in the GitHub repository killvxk/cybersecurity-skills-zh (44 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 998 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
analyzing-malware-persistence-with-autoruns
Use Sysinternals Autoruns to systematically enumerate and analyze malware persistence mechanisms across Windows registry run keys, scheduled tasks, services, drivers, and startup locations. Use when hunting for persistence during Windows incident response, triaging a compromised endpoint, or validating that malware…
analyzing-malware-persistence-with-autoruns
Use Sysinternals Autoruns to systematically identify and analyze malware persistence mechanisms across registry keys, scheduled tasks, services, drivers, and startup locations on Windows systems.
analyzing-malware-persistence-with-autoruns
Use Sysinternals Autoruns to systematically identify and analyze malware persistence mechanisms across registry keys, scheduled tasks, services, drivers, and startup locations on Windows systems.
analyzing-malware-persistence-with-autoruns
Use Sysinternals Autoruns to systematically identify and analyze malware persistence mechanisms across registry keys, scheduled tasks, services, drivers, and startup locations on Windows systems.
analyzing-malware-persistence-with-autoruns
Use Sysinternals Autoruns to systematically identify and analyze malware persistence mechanisms across registry keys, scheduled tasks, services, drivers, and startup locations on Windows systems.
analyzing-malware-persistence-with-autoruns
Use Sysinternals Autoruns to systematically identify and analyze malware persistence mechanisms across registry keys, scheduled tasks, services, drivers, and startup locations on Windows systems.