WPeGPT Analyzer

VerifiedCaution

Automated reverse analysis of binary executables (PE/ELF) using IDA and WPeGPT. Outputs structured reports including program purpose, network IoCs, suspicious functions, and vulnerability assessment.

Sby Skills Guide Bot
SecurityAdvanced
7/22/2026
Claude Code
#reverse-engineering#ida-pro#binary-analysis#malware-analysis#ioc-extraction

Recommended for

Automated summary

Drives IDA Pro through the WPeGPT plugin to automatically reverse-engineer PE/ELF binaries and emit a structured report covering program purpose, network IoCs, suspicious functions and a vulnerability assessment.

Strengths

  • Three modes (light, full, vuln) picked automatically from the intent of the request
  • Fully automated pipeline: headless IDA, WPeGPT plugin, TCP controller, then Markdown and JSON reports
  • Up-front dependency validation (IDA binaries, plugin files, config, Python) with a clear stop-and-report on anything missing
  • Surfaces network IoCs (IPs, domains, URLs, ports) and, in vuln mode, highlights vulnerability types and risk levels

Limitations

  • Windows-only: PowerShell launch script, IDA paths and %TEMP% port-file cleanup
  • Assumes a licensed IDA Pro install carrying the WPeGPT plugin plus API credentials configured outside the skill's scope, inside WPeGPT_Config/config.py
  • Runs take roughly 2 to 30 minutes depending on mode and binary size, with no usable intermediate feedback while waiting
When to use it

Reach for it when you need a fast read on an opaque binary, a malware triage pass, or a first-pass vulnerability assessment without hand-driving the reversing work.

When not to use it

Skip it for plain inspection of non-executable files, or when no licensed IDA Pro instance with the WPeGPT plugin is available.

Security analysis

Caution
Quality score82/100

The skill is a legitimate reverse-engineering orchestration wrapper: it invokes IDA and a local AI controller through a PowerShell script. There are no visible destructive, exfiltrating, or obfuscated instructions, but it uses powerful tools (headless IDA, TCP service, API credentials, local script execution), so it warrants caution rather than a safe rating.

Findings
  • •Executes an external PowerShell script (`./scripts/wpegpt_analyze.ps1`) whose contents are not shown, so its actual behavior cannot be fully audited from SKILL.md alone.
  • •Launches IDA in headless mode and coordinates via a local TCP server (`WPeServer`), which opens a local network service.
  • •Reads and relies on AI API credentials configured in `WPeGPT_Config/config.py`; careless logging or reports could expose secrets.
  • •Automatically creates/modifies `config/config.ini` and cleans temp port files, which changes local state without explicit per-run confirmation.
  • •No guidance on sandboxing when analyzing potentially malicious binaries, despite the skill being explicitly for malware/RE workflows.
How this analysis is made

Examples

Quick triage
分析一下 C:\samples\dropper.exe 是干什么的,有没有网络行为
Deep analysis
对 ./libs/service.dll 做深度分析,逐个说明关键函数的功能
Vulnerability assessment
检查 ./bin/nginx.elf 有没有漏洞,列出高危函数和风险等级

name: wpegpt-analyzer description: 驱动 IDA 配合 WPeGPT 插件对二进制可执行文件(PE/ELF)进行自动化逆向分析,输出包含程序用途、网络 IoC、可疑函数及漏洞评估的结构化报告。

wpegpt-analyzer

驱动 IDA 配合 WPeGPT AI 插件,对二进制可执行文件进行自动化逆向分析。支持 PE 和 ELF 格式,提供三种分析模式:light(轻量分析)、full(深度分析)、vuln(漏洞评估)。

何时使用

当用户要求以下操作时使用此技能:

  • 分析二进制可执行文件(.exe、.dll、.elf 等)
  • 了解一个程序的功能和用途
  • 进行逆向工程或恶意软件分析
  • 从二进制文件中提取网络 IoC(入侵指标)
  • 检查二进制文件是否存在漏洞或安全问题

何时不使用

  • 静态文件查看(使用通用文件读取工具即可)
  • 非二进制可执行文件分析

分析模式

| 模式 | 触发关键词 | 适用场景 | |------|-----------|----------| | light(默认) | 分析、看一下、了解用途、有什么功能、逆向、analyze | 轻量分析:程序用途、网络地址、可疑函数(约 2-5 分钟) | | full | 深度分析、全面分析、详细分析、deep analysis | 全量分析:所有函数的完整功能分析(约 10-30 分钟) | | vuln | 漏洞、漏洞分析、找漏洞、安全检查、安全审计、vuln、exp | 漏洞评估:高危函数、漏洞类型、风险等级(约 5-20 分钟) |

根据用户请求的语义自动选择模式。用户仅说"分析一下"或普通描述时,默认使用 light 模式。

操作步骤

1. 检查配置

读取 ./config/config.ini。如果文件不存在或 ida_dir 为空,询问用户 IDA 的安装路径,然后创建该文件:

[paths]
ida_dir=<用户提供>
python_path=<可选,Python 已在系统 PATH 中时可留空>

在继续之前验证以下依赖:

  • <ida_dir>\ida.exe 必须存在
  • <ida_dir>\plugins\WPeGPT.py 必须存在
  • <ida_dir>\plugins\WPeGPT_Config\config.py 必须存在
  • <ida_dir>\plugins\WPeGPT_Config\wpe_ai_controller.py 必须存在
  • Python 可用(已在 ./config/config.ini 配置 python_path 路径或在系统 PATH 中)

任一依赖缺失时,停止分析并报告缺失项。

2. 确认文件路径

确认用户指定的待分析二进制文件存在。如果不存在,询问用户正确路径。

3. 执行分析

运行 PowerShell 分析脚本:

powershell -NoProfile -File "./scripts/wpegpt_analyze.ps1" -BinaryPath "<binary_path>" -Mode "<mode>"

模式可选:light(默认)、full、vuln。

重要: 始终使用 powershell -NoProfile -File 调用 .ps1 脚本。不要使用 cmd.exe /c 调用 .bat 脚本,在该环境下输出会被截断。

脚本将自动完成以下步骤:

  1. 解析配置文件并验证所有依赖
  2. 检测 32 位或 64 位架构(PE 头 Machine Type 或 ELF class)
  3. 选择对应的 IDA 可执行文件(ida.exe 或 ida64.exe)
  4. 以无头模式(-A)启动 IDA,WPeGPT 插件自动加载
  5. 轮询等待 WPeServer TCP 端口文件就绪
  6. 运行 wpe_ai_controller.py 通过 TCP 驱动分析
  7. 分析完成后自动退出

4. 输出结果

报告保存在二进制文件同级目录下:<binary_dir>/<文件名>_WPeAI_Results/

读取生成的 Markdown 报告,向用户总结:

  • 程序用途:AI 综合判定的程序分类和行为特征
  • 网络 IoC:IP、域名、URL、端口(如有网络行为)
  • 可疑函数:数量及关键信息
  • 完整报告路径:.md 和 .json 报告的位置

vuln 模式下,重点突出发现的漏洞类型、风险等级和潜在利用点。

配置

./config/config.ini:

[paths]
; IDA 安装目录(必填)
ida_dir=
; Python 可执行文件路径(可选,Python 已在 PATH 中时可留空)
python_path=

IDA 进行分析时使用的 AI 模型和 API 密钥在 <ida_dir>\plugins\WPeGPT_Config\config.py 中配置(不在本技能管理范围内)。

文件结构

wpegpt-analyzer/
├── SKILL.md                  # 本文件
├── config/
│   └── config.ini            # 技能配置文件
└── scripts/
    ├── wpegpt_analyze.ps1    # PowerShell 启动脚本(推荐)
    └── wpegpt_analyze.bat    # Batch 启动脚本(备用,仅本地终端使用)

外部依赖(位于 IDA 安装目录的 plugins 子目录):

<ida_dir>/plugins/
├── WPeGPT.py                 # IDA 插件(含 WPeServer TCP 服务)
└── WPeGPT_Config/
    ├── config.py             # WPeGPT 使用的 AI 模型 / API 配置文件
    └── wpe_ai_controller.py  # 外部 AI 控制器(驱动 IDA 进行自动化分析)

注意事项

  • 非交互模式:分析流程全自动运行,所有配置必须提前写入 config.ini。首次运行时由本技能的"步骤 1"负责交互式创建配置文件。
  • 无头模式:IDA 以最小化方式启动(-A 标志)。WPeGPT 插件自动启动 WPeServer,控制器通过 TCP 与其通信。
  • 耗时参考:light 模式约 2-5 分钟,full/vuln 模式约 5-30 分钟(取决于二进制文件大小)。
  • API 密钥:AI 分析依赖 WPeGPT_Config/config.py 中配置的有效 API 凭证。
  • 环境清理:每次运行前自动清理 %TEMP% 下的旧端口文件。

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/wpegpt-analyzer-mrwakf7m/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/wpegpt-analyzer-mrwakf7m' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/wpegpt-analyzer-mrwakf7m/download' --output '.skill-downloads/wpegpt-analyzer-mrwakf7m/SKILL.md.part' && mv '.skill-downloads/wpegpt-analyzer-mrwakf7m/SKILL.md.part' '.skill-downloads/wpegpt-analyzer-mrwakf7m/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/wpegpt-analyzer-mrwakf7m/SKILL.md' && test -s '.skill-downloads/wpegpt-analyzer-mrwakf7m/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/wpegpt-analyzer' && cp -R '.skill-downloads/wpegpt-analyzer-mrwakf7m' '.claude/skills/wpegpt-analyzer'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/wpegpt-analyzer-mrwakf7m'

openskills read 'wpegpt-analyzer-mrwakf7m'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/wpegpt-analyzer-mrwakf7m/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills