Detects prompt injection using regex signature matching, heuristic scoring for structural anomalies, and DeBERTa-based transformer classification, flagging direct injections (system-prompt overrides, role-play escapes) and indirect injections (encoded payloads, obfuscation) per OWASP LLM Top 10 (LLM01:2025).
Install
npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-ai-model-prompt-injection-attacksnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-ai-model-prompt-injection-attacks -a claude-code -gnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-ai-model-prompt-injection-attacks -a codex -ggemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/detecting-ai-model-prompt-injection-attacksgh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-ai-model-prompt-injection-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-ai-model-prompt-injection-attacks ~/.claude/skills/detecting-ai-model-prompt-injection-attacks # Claude Code
cp -R /tmp/mukul975__Anthropic-Cybersecurity-Skills/skills/detecting-ai-model-prompt-injection-attacks ~/.agents/skills/detecting-ai-model-prompt-injection-attacks # Codex, Cursor, Gemini CLI, Copilot, OpenCode