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 Asaiuta/reverse-workbench-skill --skill ghidra-headlessgit clone --depth 1 https://github.com/Asaiuta/reverse-workbench-skillWrote 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/asaiuta/reverse-workbench-skill/ghidra-headless)<a href="https://agentmods.dev/skills/asaiuta/reverse-workbench-skill/ghidra-headless"><img src="https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/ghidra-headless/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/asaiuta/reverse-workbench-skill/ghidra-headless"><img src="https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/ghidra-headless.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 | $0.00107 | $0.00978 |
| Opus 5 | $0.00053 | $0.00489 |
| Sonnet 5 | $0.00021 | $0.00196 |
| Haiku 4.5 | $0.00011 | $0.00098 |
Grade A, and why
ghidra-headless scanned grade A with 0 findings 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 5d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ghidra 无头批量分析
该模块将项目内经过验证的 Ghidra Java 导出脚本纳入全局工具链。它用于可复现的初筛和证据导出,不替代对关键函数的手工反汇编、动态验证或跨反编译器交叉确认。
入口与依赖
- 先运行
archive-file-triage/对未知输入记录类型、大小和 SHA-256。 - 读取
../tool-index.md,以其中的analyzeHeadless实际路径为准;不得猜测 Ghidra 安装路径。 - 若工具缺失,按
skills/scripts/bootstrap-reverse.ps1的ghidra-mcp/Ghidra 能力流程安装或配置后再执行。
资源:
scripts/ghidra-analyze.ps1 Windows 原生包装器
scripts/ghidra-analyze.sh Linux/WSL 包装器
scripts/ghidra_scripts/ExportAll.java 聚合导出
scripts/ghidra_scripts/ExportDecompiled.java
scripts/ghidra_scripts/ExportFunctions.java
scripts/ghidra_scripts/ExportStrings.java
scripts/ghidra_scripts/ExportCalls.java
scripts/ghidra_scripts/ExportSymbols.java
标准工作流
初筛优先使用 ExportAll.java,把结果写入任务专属目录:
$skill = ".\skills\ghidra-headless" # 相对于技能根目录
& (Join-Path (Resolve-Path $skill) "scripts\ghidra-analyze.ps1") `
-Script ExportAll.java `
-OutputDirectory .\artifacts\sample `
-Binary .\sample.exe
按需导出单项产物:
& "$skill\scripts\ghidra-analyze.ps1" -Script ExportStrings.java -OutputDirectory .\artifacts\sample -Binary .\sample.exe
& "$skill\scripts\ghidra-analyze.ps1" -Script ExportFunctions.java -OutputDirectory .\artifacts\sample -Binary .\sample.exe
对架构判断错误或裸固件,可显式指定 processor,例如 -Processor 'ARM:LE:32:v7';仅在已经确认格式且需要加速时使用 -NoAnalysis。
标准产物
ExportAll.java 会按输入基名产生下列可归档产物(具体扩展名以脚本输出为准):
<name>_summary.txt
<name>_decompiled.c
<name>_functions.json
<name>_strings.json 或 <name>_strings.txt
<name>_symbols.json
<name>_calls.json
<name>_interesting.txt
ghidra_analysis.log
ghidra_output.log
先读 *_summary.txt 和 *_interesting.txt,再根据字符串、导入、函数和调用关系锁定关键函数。重要结论应带文件路径、函数名/地址与原始证据;反编译结果只是近似 C,不应单独作为最终结论。
后续路由
- 需要 CLI 深挖、脚本化反汇编或快速交叉验证 →
radare2/。 - 需要 IDA 数据库、反编译或 MCP →
ida-reverse/。 - 需要调试、Hook、内存或行为验证 →
reverse-engineering/tools-dynamic.md。 - 输入是固件 → 先进入
firmware-pentest/;输入是 APK 中的.so→ 回到apk-reverse/的 Native 分支。
输出要求
报告输入哈希、Ghidra 实际路径、包装器命令、processor/cspec、产物目录、关键函数/地址、结论与仍需动态验证的假设。
What ships with it
8 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.
- scripts/ghidra_scripts/ExportAll.java 11 KB
- scripts/ghidra_scripts/ExportCalls.java 5.3 KB
- scripts/ghidra_scripts/ExportDecompiled.java 3.1 KB
- scripts/ghidra_scripts/ExportFunctions.java 4.8 KB
- scripts/ghidra_scripts/ExportStrings.java 4.4 KB
- scripts/ghidra_scripts/ExportSymbols.java 5.7 KB
- scripts/ghidra-analyze.ps1 3.8 KB runs code
- scripts/ghidra-analyze.sh 6.3 KB runs code
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.
- 5d ago First seen · 78 lines · 107 tokens per session scan A ce65afe86c72
ghidra-headless is a skill published in the GitHub repository Asaiuta/reverse-workbench-skill (2 stars, last pushed 25d ago), licensed MIT. It adds 107 tokens to every session and 978 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
osint-recon
A knowledge guide for open-source intelligence, or OSINT: collecting information from publicly available sources. It covers servers, websites, domains, and, when appropriate, people.
hackerone
A safety wrapper for HackerOne bug-bounty testing that reads a program's allowed targets and rules before handing each allowed asset to a penetration-testing workflow. HackerOne is a platform where companies invite researchers to report security bugs.
crypto-toolkit
A toolkit for encoding, decoding, hashing, and encrypting data in formats such as Base64, hexadecimal, URLs, JWTs, AES, RSA, and common ciphers.
redteam-cve-lookup
CVE lookup and applicability assessment domain card. Use after reconnaissance has identified products, versions, services, or fingerprints and red-team mode needs evidence-based CVE matching before deeper testing.
redteam-cve-validation
CVE validation domain card. Use after CVE lookup has produced applicable or candidate CVEs and red-team mode needs scoped evidence to decide whether to continue, pivot, or report.
secknowledge-skill
A knowledge base for testing the security of websites, software, and AI systems, including agents and language models.