code-injection

Name: code-injection
Availability: InStock
Author: plugin

Detect code-injection vulnerabilities in AI systems with controlled payloads.

3|Updated Nov 18, 2025

Search Tags:#payloads #security-testing #vulnerability-analysis #code-injection #attack-simulation #LLM-safety

Ready to run

npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill code-injection

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: code-injection
Source: https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming/tree/main/skills/code-injection
Command: npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill code-injection

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill detects and tests code-injection vulnerabilities in AI systems by simulating controlled payloads and analyzing responses to identify unsafe patterns.

Core Features & Use Cases

Payload-based testing across code generation, agent tools, template engines, and NL-to-SQL to reveal injection vectors.
Vulnerability reporting with vectors tested, count of vulnerabilities found, and severity breakdown to guide remediation.
Use Case: A security engineer validates an AI assistant's defenses against prompt-to-code and tool-exploitation attempts before deployment.

Quick Start

Load this skill and run a baseline test against target_type code_gen with language python to observe vulnerability metrics and recommended mitigations.

Frequently Asked Questions about code-injection

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I test AI systems for code-injection vulnerabilities?▼

Test code-injection vulnerabilities by executing controlled payloads against defined AI targets. This skill simulates attacks across code generation, agent tools, template engines, and NL-to-SQL vectors to identify unsafe patterns.

What attack vectors are covered in AI vulnerability analysis?▼

AI vulnerability analysis covers code generation, agent tools, template engines, and NL-to-SQL attack vectors. It tests payloads across python, javascript, sql, and bash to model real-world attack surfaces.

How do I detect prompt-to-code injection attempts before deployment?▼

Detect prompt-to-code injection attempts by simulating controlled payloads and analyzing AI responses. Security engineers validate assistant defenses against tool-exploitation attempts to find unsafe patterns before deployment.

Does this security-testing skill output metrics suitable for CI dashboards?▼

Yes, this security-testing skill outputs structured metrics suitable for CI dashboards. It provides vectors tested, vulnerabilities found, and a severity breakdown to guide remediation efforts.

How do I run a baseline vulnerability analysis for python code generation?▼

Run a baseline vulnerability analysis by testing target_type code_gen with language python. This observes vulnerability metrics and recommended mitigations for your AI system's code generation flow.