Detects prompt injection hidden in documents from the other side (pleadings, skeletons, bundles, served evidence, opponents' emails and attachments) before an AI reads them, so the model is not turned against your client.
Install
npx skills add lawve-ai/awesome-legal-skills --skill pleading-injection-guardnpx skills add lawve-ai/awesome-legal-skills --skill pleading-injection-guard -a claude-code -gnpx skills add lawve-ai/awesome-legal-skills --skill pleading-injection-guard -a codex -ggemini skills install https://github.com/lawve-ai/awesome-legal-skills.git --path skills/pleading-injection-guard-matei-clejgh skill install lawve-ai/awesome-legal-skills pleading-injection-guardgit 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/pleading-injection-guard-matei-clej ~/.claude/skills/pleading-injection-guard # Claude Code
cp -R /tmp/lawve-ai__awesome-legal-skills/skills/pleading-injection-guard-matei-clej ~/.agents/skills/pleading-injection-guard # Codex, Cursor, Gemini CLI, Copilot, OpenCode