skills.rest
pluginagentmarketplace
pluginagentmarketplaceCOMMUNITY
Explore all skills by this author →
GitHub

vulnerability-discovery

Identify and analyze AI/LLM vulnerabilities via structured threat modeling and attack surface analysis.

3|Updated Nov 18, 2025
Search Tags:#OWASP#vulnerability#LLM#risk-assessment#threat-modeling#attack-surface#security-analysis
One-click install
npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill vulnerability-discovery
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vulnerability-discovery
Source: https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming/tree/main/skills/vulnerability-discovery
Command: npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill vulnerability-discovery

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Systematic vulnerability discovery for AI/LLM systems through structured threat modeling, attack surface analysis, and OWASP LLM Top 10 alignment.

Core Features & Use Cases

  • Threat modeling integration and risk assessment mapping for LLM deployments
  • Attack surface discovery and evidence-based vulnerability listing
  • Use Case: Red team exercises and secure plugin evaluations for AI assistants

Quick Start

vulnerability-discovery --target https://api.example.com --output scan.json

Frequently Asked Questions about vulnerability-discovery

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

FAQPage Schema
How do I discover vulnerabilities in LLM applications using OWASP mappings?▼

You discover LLM vulnerabilities by applying structured threat modeling and attack surface analysis to map system risks against the OWASP LLM Top 10, producing structured vulnerability findings for security testing.

What is structured threat modeling for AI systems?▼

Structured threat modeling for AI systems systematically identifies and analyzes LLM vulnerabilities across the attack surface, assessing risks to secure deployments during red team exercises and plugin evaluations.

How do I run a risk assessment on an LLM API endpoint?▼

Run a risk assessment on an LLM API endpoint by executing vulnerability discovery with a defined target URL, analyzing the attack surface and outputting structured vulnerability findings to a JSON file.

Does this vulnerability discovery skill work for red team exercises?▼

Vulnerability discovery supports red team exercises by performing structured threat modeling and attack surface analysis to identify and map AI vulnerabilities against the OWASP LLM Top 10 framework.

What is the best way to analyze an LLM attack surface?▼

The best way to analyze an LLM attack surface is through evidence-based vulnerability listing integrated with risk assessment mapping, systematically discovering threats aligned with the OWASP LLM Top 10.

Related Skills

Explore More Software Engineering Skills→
cdalsoniiicdalsoniii

Attack Surface Map

Enumerate API endpoints and document authentication, validation, rate limits, and data sensitivity.

Community
Advanced
dnvitidnviti
10

vulnerability-create

Generate structured remediation tasks from security vulnerability findings with severity classification.

Community
Intermediate
ArianHobson333ArianHobson333
7

injection

Detect and exploit NoSQL and OS Command injection vulnerabilities in web applications.

Community
Advanced
pradyumnasagarpradyumnasagar
6

agent-handoff

Automate inter-skill data transfer and provenance capture via JSON Material Passports.

Community
Advanced