# AI Platforms

> Covers attacking AI systems across recon of endpoints and APIs, threat modeling agent permissions, finding vulns in LLMs and RAG, exploiting AI infra, and poisoning supply chains

- **URL:** https://hackindex.io/platforms/ai
- **Type:** Platform
- **Tags:** ai, cloud, api, web, machine-learning
- **Published:** 2026-03-18
- **Updated:** 2026-07-13

AI and machine learning systems introduce a new class of attack surfaces to pentesting. As organizations deploy large language models (LLMs), ML inference APIs, and AI-powered applications, these systems become targets for prompt injection, model manipulation, and data extraction. AI security testing requires understanding both traditional application security and the unique behaviors of ML models.

AI-specific attacks focus on prompt injection (direct and indirect), jailbreaking model safety filters, training data extraction, model inversion, adversarial inputs that cause misclassification, and supply chain risks from poisoned models or compromised model repositories. LLM-integrated applications are particularly vulnerable where user input reaches the model alongside system prompts or retrieval-augmented generation (RAG) context.

This section covers AI security testing techniques: enumeration of model capabilities, system prompts, and tool integrations, exploitation through prompt injection to bypass access controls or exfiltrate data, manipulation of AI-powered decision systems, and assessment of ML supply chain risks including model provenance and dependency poisoning.

## Phases

- [Reconnaissance](https://hackindex.io/platforms/ai/reconnaissance.md): Guides for mapping AI endpoints, models, APIs, and dependencies (6 guides)
- [Threat Modeling](https://hackindex.io/platforms/ai/threat-modeling.md): Guides on mapping AI trust boundaries, agent permissions, and targets (5 guides)
- [Vulnerability Discovery](https://hackindex.io/platforms/ai/vulnerability-discovery.md): Guides covering vuln discovery in LLM, RAG, MCP, and AI infra (6 guides)
- [Exploitation](https://hackindex.io/platforms/ai/exploitation.md): Exploit LLM apps, RAG pipelines, agents, and AI infrastructure (31 guides)
- [Post-Exploitation](https://hackindex.io/platforms/ai/post-exploitation.md): Guides on persistence, pivoting, and data extraction from AI systems (5 guides)
- [Supply Chain Attacks](https://hackindex.io/platforms/ai/supply-chain-attacks.md): Guides on poisoning datasets, weights, adapters, and pipelines (5 guides)