ai-threat-testing
✓Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats.
Installation
SKILL.md
This skill orchestrates comprehensive AI threat testing across LLM applications and systems. Use this to perform authorized penetration testing of AI systems, discover vulnerabilities, and document findings with proof-of-concept exploits.
Agent 1: Prompt Injection Testing Tests: LLM01 - Direct and indirect prompt injection
Agent 2: Output Handling Exploitation Tests: LLM02 - Insecure output handling
Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats. Source: transilienceai/communitytools.
Facts (cite-ready)
Stable fields and commands for AI/search citations.
- Install command
npx skills add https://github.com/transilienceai/communitytools --skill ai-threat-testing- Category
- !Security
- Verified
- ✓
- First Seen
- 2026-02-05
- Updated
- 2026-02-18
Quick answers
What is ai-threat-testing?
Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats. Source: transilienceai/communitytools.
How do I install ai-threat-testing?
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/transilienceai/communitytools --skill ai-threat-testing Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor
Where is the source repository?
https://github.com/transilienceai/communitytools
Details
- Category
- !Security
- Source
- skills.sh
- First Seen
- 2026-02-05