← All skills

re-ai-attack

85 / 100 · Low risk

Fine to try.

By dslsdzc/rev-skills (GitHub) · security · 240 stars · scanned at commit 1977504

AI 模型安全评估与取证（行为层）：extraction assessment（API 黑盒提取评估）、 fingerprint verification（行为指纹与归属验证）、privacy leakage evaluation（成员推断/隐私泄露评估）、 robustness evaluation（对抗鲁棒性评估）。 触发词：API模型窃取、黑盒模型复制、模型指纹、成员推断、对抗样本、行为水印、模型安全评估、隐私泄露评估。

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'re-ai-attack' ] || [ -L ~/.agents/skills/'re-ai-attack' ]; then echo 'A skill folder named re-ai-attack already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/dslsdzc/rev-skills' "$d" && git -C "$d" checkout --quiet '1977504515d3f5fa8889da43974feb7a0f4eaab9' -- '.claude/skills/re-ai-attack' && mkdir -p ~/.agents/skills && cp -R "$d"/'.claude/skills/re-ai-attack' ~/.agents/skills/'re-ai-attack' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'re-ai-attack' ~/.claude/skills/'re-ai-attack' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for dslsdzc/rev-skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/dslsdzc/rev-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/dslsdzc/rev-skills/)

Score history