Detecting AI Model Prompt Injection Attacks
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison''s promp
Install
npx skills add adriannoes/awesome-agentic-ai --skill detecting-ai-model-prompt-injection-attacksgit clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai.git /tmp/awesome-agentic-ai
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-agentic-ai/cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/detecting-ai-model-prompt-injection-attacks ~/.claude/skills/detecting-ai-model-prompt-injection-attacksPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Detecting AI Model Prompt Injection Attacks ## When to Use - Scanning user inputs to LLM-powered applications before they are forwarded to the model - Building an input validation layer for chatbots, AI agents, or retrieval-augmented generation (RAG) pipelines - Monitoring logs of LLM interactions to retrospectively identify prompt injection attempts - Evaluating the effectiveness of existing prompt injection defenses through red-team testing - Classifying prompt injection payloads during security incident investigations involving AI systems **Do not use** as the sole defense mechanism against prompt injection -- always combine with output validation, privilege separation, and least-privilege tool access. Not suitable for detecting jailbreaks that do not involve injection of adversarial instructions. ## Prerequisites - Python 3.10+ with pip for installing detection dependencies - The `transformers` and `torch` libraries for running the DeBERTa-based classifier model - The `protectai/deberta-v3-base-prompt-injection-v2` model from Hugging Face (downloaded on first run, approximately 700 MB) - Network access to Hugging Face Hub for initial model download (offline mode supported after first download) - Sample prompt injection payloads for testing (the script includes a built-in test suite) ## Workflow ### Step 1: Install Detection Dependencies Install the required Python packages for all three detection layers:
Details
- Skill name
detecting-ai-model-prompt-injection-attacks- Repository
- adriannoes/awesome-agentic-ai
- Path
cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/detecting-ai-model-prompt-injection-attacks/SKILL.md- License
- MIT
- Repo updated
- 2 November 2026
FAQ
What does the Detecting AI Model Prompt Injection Attacks skill do?
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison''s promp
How do I install the Detecting AI Model Prompt Injection Attacks skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add adriannoes/awesome-agentic-ai --skill detecting-ai-model-prompt-injection-attacks. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Detecting AI Model Prompt Injection Attacks popular?
It lives in adriannoes/awesome-agentic-ai, which has 100 GitHub stars and 27 forks, and is included in 2 curated skill lists.
Related skills
Browserstack
100adriannoes/awesome-agentic-ai
Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".
Coverage
100adriannoes/awesome-agentic-ai
Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".
Fix
100adriannoes/awesome-agentic-ai
Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".
Detecting Data and Model Poisoning
100adriannoes/awesome-agentic-ai
Identify poisoned training data and backdoored models across the ML pipeline.
Delegating to Agents
100adriannoes/awesome-agentic-ai
How to delegate work to another AI agent (Pi, Codex, Claude Code, Hermes) — picking the right agent, sending prompts to TUI agents, polling progress. Read BEFORE any `cmux send`/`tmux send-keys` to an agent, or whenever delegating, relaying, spawning, or orchestrating agent-to-agent work.
Detecting Indirect Prompt Injection
100adriannoes/awesome-agentic-ai
Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.