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 dslsdzc/rev-skills --skill re-ai-triagegit clone --depth 1 https://github.com/dslsdzc/rev-skillsWrote 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/dslsdzc/rev-skills/re-ai-triage)<a href="https://agentmods.dev/skills/dslsdzc/rev-skills/re-ai-triage"><img src="https://agentmods.dev/badge/skills/dslsdzc/rev-skills/re-ai-triage/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/dslsdzc/rev-skills/re-ai-triage"><img src="https://agentmods.dev/badge/skills/dslsdzc/rev-skills/re-ai-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.01229 |
| Opus 5 | $0.00044 | $0.00615 |
| Sonnet 5 | $0.00017 | $0.00246 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
re-ai-triage 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 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.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 模型分析入口（分流器）
任务分类器（输入形态 → 路径）
拿到 AI 相关目标后先判输入形态，命中即转对应技能：
| 输入形态 | 路径 |
|---|---|
| 拿到模型文件（.onnx / .pt / .pth / .safetensors / .tflite） | → [[re-ai-model]]（文件层：格式解析 / 结构还原 / 权重提取 / 文件级水印） |
| 只有 API（无文件，黑盒接口） | → [[re-ai-attack]]（行为层：extraction / fingerprint / privacy / robustness 评估；guard 授权前置） |
| 文件 + API 都有 | → 先 [[re-ai-model]]（文件侧取证）→ 再 [[re-ai-attack]]（行为侧验证） |
| 发现恶意行为（投毒 / 后门 / 恶意载荷 / 下载执行） | → 恶意分析（当前：[[re-ai-model]] 安全边界处理 + [[re-behavior]]；未来独立 re-ai-malware 承接） |
| 模型被打包进可执行（PyInstaller/pyarmor 等） | → 先 [[re-binary-core]] 拆包 → 拆出的模型文件回本技能分流 |
何时使用 / 何时不用
- 用：用户说「分析这个模型 / AI 模型安全 / 模型泄露」但未指明输入形态——先分流
- 用：不确定目标是文件层还是行为层时——先识别再转
- 不用：输入形态已明确（直接进 [[re-ai-model]] 或 [[re-ai-attack]]，不绕本技能）
- 不用：非 AI 目标（走全局入口 [[re-analyze]]）
- 不用：训练 / 微调 / 部署（非逆向）
工具准备
本技能只做识别与分流，工具轻量：
python3 / file —— 模型文件识别
- python3 安装与验证见 [[re-python]] 工具准备
file：Linuxapt install file/dnf install file/pacman -S file（多数预装）；验证file --version- 验证：
python3 -c "import struct"（标准库）
模型库探测（判断目标依赖，不加载模型）
pip list 2>/dev/null | grep -iE 'torch|tensorflow|onnx'——确认本机可解析目标格式；缺失时由下游技能引导安装
操作步骤
- 输入形态识别：
- 用户给了路径/文件 → 先
file <path>（onnx：file常报data——以xxd首字节 protobuf 头（08 08）+stringsproducer 名辅助识别；safetensors：JSON metadata头；pt/pth：pickle或 zip 容器；tflite：tflite标识）→ 转 [[re-ai-model]] - 用户只有 API 端点/查询能力 → 转 [[re-ai-attack]]
- 两者都有 → 按任务分类器先文件后行为
- 用户给了路径/文件 → 先
- 目标归属确认：文件/API 的持有方与授权（自有 / 授权测试 / CTF·研究）——行为层评估前必须确认（[[re-ai-attack]] guard 前置；授权上下文见 triage 第 0 步
RE_AUTH） - 转交与记录：明确转交技能 + 会话变量（
RE_GOAL、RE_AUTH、输入形态标记），不在本技能做深度分析
跨域联合
- [[re-managed]]：本技能是其 AI 分支的第一跳（re-managed → re-ai-triage → re-ai-model / re-ai-attack）
- [[re-ai-model]]：文件层下游
- [[re-ai-attack]]：行为层下游（guard 授权前置）
- [[re-binary-core]]：模型打包进可执行时的拆包前置
- [[re-behavior]]：恶意行为侧协作（投毒/后门的行为判定）
常见坑与陷阱
- 拿文件名猜格式：
.pt可能是 pickle 也可能是 zip 容器（torch 新格式）、.bin可能是任意权重 dump——以file输出与魔数为准，不靠扩展名 - 分流过深：本技能只识别与转交，不展开分析——在分流阶段做深度分析会与下游重复
- 授权前置遗漏：行为层评估（[[re-ai-attack]]）有 guard 授权要求——转交前先确认
RE_AUTH，未知归属时先询问，不直接进入行为层
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 · 69 lines · 87 tokens per session scan A 326c7e126413
re-ai-triage is a skill published in the GitHub repository dslsdzc/rev-skills (52 stars, last pushed 13d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,229 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
ctf-ai-ml
Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or…
ai-data-security
A security-testing method for AI systems that examines data leaks, training-data exposure, and the integrity of retrieval-augmented generation (RAG) or vector databases. A vector database stores data in a form AI systems use to find related information.
prompt-injection
A security-testing method for indirect prompt injection, where instructions hidden in webpages, documents, emails, databases, or API responses influence an AI system. It also covers attacks on connected tools, retrieved data, and information handling.