# Detecting AI model prompt injection attacks

> Detecting AI model prompt injection attacks is an open-source agent skill for ai models and llm tooling. Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known a. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/plurigrid/asi/tree/main/plugins/asi/skills/detecting-ai-model-prompt-injection-attacks
- **Repository:** https://github.com/plurigrid/asi
- **GitHub stars:** 72
- **License:** Apache-2.0
- **Skill name:** detecting-ai-model-prompt-injection-attacks
- **Collection:** https://github.com/plurigrid/asi
- **Categories:** AI models and LLM tooling
- **Listing updated:** 2026-11-17

## About

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 prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.

## When your agent uses it

> 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 prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/plurigrid/asi/tree/HEAD/plugins/asi/skills/detecting-ai-model-prompt-injection-attacks)
- [License: Apache-2.0](https://github.com/plurigrid/asi/tree/HEAD/plugins/asi/skills/detecting-ai-model-prompt-injection-attacks)

## Install

### Claude Code

This skill ships in the `asi` plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):

```sh
/plugin marketplace add plurigrid/asi
/plugin install asi@asi
```

Or copy only this skill to `~/.claude/skills/detecting-ai-model-prompt-injection-attacks`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/detecting-ai-model-prompt-injection-attacks &&
cp -R "$tmp/plugins/asi/skills/detecting-ai-model-prompt-injection-attacks" ~/.claude/skills/detecting-ai-model-prompt-injection-attacks &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/detecting-ai-model-prompt-injection-attacks` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/detecting-ai-model-prompt-injection-attacks` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/detecting-ai-model-prompt-injection-attacks &&
cp -R "$tmp/plugins/asi/skills/detecting-ai-model-prompt-injection-attacks" ~/.agents/skills/detecting-ai-model-prompt-injection-attacks &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/detecting-ai-model-prompt-injection-attacks` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/detecting-ai-model-prompt-injection-attacks` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/detecting-ai-model-prompt-injection-attacks &&
cp -R "$tmp/plugins/asi/skills/detecting-ai-model-prompt-injection-attacks" ~/.cursor/skills/detecting-ai-model-prompt-injection-attacks &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/detecting-ai-model-prompt-injection-attacks` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/plurigrid/asi.git --path plugins/asi/skills/detecting-ai-model-prompt-injection-attacks
```

Or copy the folder to `~/.gemini/skills/detecting-ai-model-prompt-injection-attacks` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/detecting-ai-model-prompt-injection-attacks`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/detecting-ai-model-prompt-injection-attacks &&
cp -R "$tmp/plugins/asi/skills/detecting-ai-model-prompt-injection-attacks" ~/.copilot/skills/detecting-ai-model-prompt-injection-attacks &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/detecting-ai-model-prompt-injection-attacks` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/plurigrid/asi.git
```

Then copy `asi/plugins/asi/skills/detecting-ai-model-prompt-injection-attacks` into your agent's skills folder as `detecting-ai-model-prompt-injection-attacks`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Detecting AI model prompt injection attacks in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/detecting-ai-model-prompt-injection-attacks to use it in all your projects, or to .claude/skills/detecting-ai-model-prompt-injection-attacks in one project. Or install the asi plugin, which includes it: /plugin marketplace add plurigrid/asi, then /plugin install asi@asi.

### Does Detecting AI model prompt injection attacks run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Detecting AI model prompt injection attacks?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to Detecting AI model prompt injection attacks?

The closest alternatives to Detecting AI model prompt injection attacks are Academy guide, MCP builder, Claude API, Nano banana pro openrouter and Generate image.

## Alternatives

- [Academy guide](https://ai-powered.com/skills/academy-guide): Academy guide is an agent skill for ai models and llm tooling.
- [MCP builder](https://ai-powered.com/skills/mcp-builder): MCP builder is an agent skill for ai models and llm tooling.
- [Claude API](https://ai-powered.com/skills/claude-api): Claude API is an agent skill for ai models and llm tooling.
- [Nano banana pro openrouter](https://ai-powered.com/skills/nano-banana-pro-openrouter): Nano banana pro openrouter is an open-source agent skill for design and media.
- [Generate image](https://ai-powered.com/skills/generate-image): Generate image is an open-source agent skill for design and media.
- [Phoenix evals](https://ai-powered.com/skills/phoenix-evals): Phoenix evals is an open-source agent skill for ai models and llm tooling.
- [Tldr prompt](https://ai-powered.com/skills/tldr-prompt): Tldr prompt is an open-source agent skill for ai models and llm tooling.
- [Arize AI provider integration](https://ai-powered.com/skills/arize-ai-provider-integration): Arize AI provider integration is an open-source agent skill for ai models and llm tooling.

---
Source: https://ai-powered.com/skills/detecting-ai-model-prompt-injection-attacks
