Prompt Injection Detection

Prompt Injection Detection is an AI Engineering skill for Claude Code, published by xalgord in xalgorix.

852 stars151 forkson xalgord/xalgorixAdded 2026/07/20+1% in starsRepository updated 2026/08/04

ai-agentai-securityautomationautonomous-pentestingbug-bountycybersecurityethical-hackinggolangpenetration-testingpentestpentesting-toolsreconsecuritysecurity-researchsecurity-toolstypescriptvulnerability-detectionvulnerability-scanner

Install in seconds

Install Prompt Injection Detection

Copy Prompt Injection Detection into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/xalgorix/xalgorix/tree/main/internal/tools/skills/data/ai-security/detecting-ai-model-prompt-injection-attacks ~/.claude/skills/detecting-ai-model-prompt-injection-attacks

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/xalgorix/xalgorix.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: internal/tools/skills/data/ai-security/detecting-ai-model-prompt-injection-attacks/SKILL.md in xalgord/xalgorix
Installs to: ~/.claude/skills/detecting-ai-model-prompt-injection-attacks
Collection: One of 51 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Prompt Injection Detection does

A multi-layered detector combining regex, heuristic scoring, and a DeBERTa classifier to identify prompt injection attacks in LLM-powered applications. Use it to scan user inputs, audit logs, or integrate as a pre-processing filter.

Prompt Injection Detection is cataloged under AI Engineering on DirSkills. Prompt Injection Detection comes from a repository tagged ai-agent, ai-security, automation, autonomous-pentesting and bug-bounty.

Documentation

README

Excerpt

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

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Prompt Injection Detection

What else does xalgord publish alongside Prompt Injection Detection?
Prompt Injection Detection is one of 51 skills that DirSkills catalogs from xalgord/xalgorix, the repository it ships in. Its siblings there include AFL++ Fuzzing, AI Security Guardrails and AI-Assisted Vulnerability Discovery. Each one is a separate skill with its own page in this directory, installs the same way Prompt Injection Detection does, and is maintained by xalgord in that same repository. The rest of the collection is listed on the xalgord/xalgorix page.
How does Prompt Injection Detection compare to other AI Engineering skills?
Prompt Injection Detection ranks #1531 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Prompt Injection Detection against them. Open each page to compare what they document and how they install.