security-review-owasp-ai-agent-security

Community

Find AI agent security gaps fast.

Authorsjinks
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps reviewers assess AI agent systems for security weaknesses such as prompt injection, unsafe tool execution, context leakage, and weak operational guardrails.

Core Features & Use Cases

  • Trust Boundary Review: Analyzes how user input, retrieved content, tools, memory, and model outputs interact across the agent workflow.
  • Abuse Path Detection: Identifies paths that could enable secret exposure, policy bypass, unauthorized actions, or unsafe autonomous behavior.
  • Evidence-Based Reporting: Produces findings with severity, confidence, affected area, evidence, impact, and remediation guidance for security reviews.

Quick Start

Use the security-review-owasp-ai-agent-security skill to review the provided AI agent flow for prompt injection and unsafe tool usage.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: security-review-owasp-ai-agent-security
Download link: https://github.com/sjinks/ai-owasp-skillset/archive/main.zip#security-review-owasp-ai-agent-security

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 536,000+ vetted skills library on demand.