Detect direct prompt injection or instruction override via user message (no external content). Focuses on system/role override attempts.
Install
npx skills add Tencent/AI-Infra-Guard --skill direct-injection-detectionnpx skills add Tencent/AI-Infra-Guard --skill direct-injection-detection -a claude-code -gnpx skills add Tencent/AI-Infra-Guard --skill direct-injection-detection -a codex -ggemini skills install https://github.com/Tencent/AI-Infra-Guard.git --path agent-scan/agent_scan/prompt/skills/direct-injection-detectiongh skill install Tencent/AI-Infra-Guard direct-injection-detectiongit clone --depth 1 https://github.com/Tencent/AI-Infra-Guard /tmp/Tencent__AI-Infra-Guard
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Tencent__AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/direct-injection-detection ~/.claude/skills/direct-injection-detection # Claude Code
cp -R /tmp/Tencent__AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/direct-injection-detection ~/.agents/skills/direct-injection-detection # Codex, Cursor, Gemini CLI, Copilot, OpenCode