Detect MITRE ATLAS AML.T0024 attacks (model stealing, inversion, membership inference) performed via inference-API abuse, by monitoring per-principal query volume/distribution, rate-limiting and perturbing outputs, and red-teaming your model's extractability.
安装
npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-model-extraction-attacksnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-model-extraction-attacks -a claude-code -gnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-model-extraction-attacks -a codex -ggemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/detecting-model-extraction-attacksgh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-model-extraction-attacksgit clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills /tmp/mukul975__Anthropic-Cybersecurity-Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/mukul975__Anthropic-Cybersecurity-Skills/skills/detecting-model-extraction-attacks ~/.claude/skills/detecting-model-extraction-attacks # Claude Code
cp -R /tmp/mukul975__Anthropic-Cybersecurity-Skills/skills/detecting-model-extraction-attacks ~/.agents/skills/detecting-model-extraction-attacks # Codex, Cursor, Gemini CLI, Copilot, OpenCode