Reviews public or shared AI-backed web endpoints for abuse, excessive cost, data exposure, unsafe browser control, weak request limits, and missing human approval. Use before launching or materially changing an HTTP or API endpoint that can invoke an AI model. Do not use as a penetration test, compliance certification, or substitute for runtime monitoring and professional security review.
Install
npx skills add lawve-ai/awesome-legal-skills --skill public-legal-ai-endpoint-protectionnpx skills add lawve-ai/awesome-legal-skills --skill public-legal-ai-endpoint-protection -a claude-code -gnpx skills add lawve-ai/awesome-legal-skills --skill public-legal-ai-endpoint-protection -a codex -ggemini skills install https://github.com/lawve-ai/awesome-legal-skills.git --path skills/public-legal-ai-endpoint-protection-adrian-lerergh skill install lawve-ai/awesome-legal-skills public-legal-ai-endpoint-protectiongit clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills /tmp/lawve-ai__awesome-legal-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/lawve-ai__awesome-legal-skills/skills/public-legal-ai-endpoint-protection-adrian-lerer ~/.claude/skills/public-legal-ai-endpoint-protection # Claude Code
cp -R /tmp/lawve-ai__awesome-legal-skills/skills/public-legal-ai-endpoint-protection-adrian-lerer ~/.agents/skills/public-legal-ai-endpoint-protection # Codex, Cursor, Gemini CLI, Copilot, OpenCode