AI Platforms:

Vulnerability Discovery

Guides covering vuln discovery in LLM, RAG, MCP, and AI infra

6 guides • Created Mar 18, 2026 • Updated Mar 29, 2026

6 guides

Detecting Insecure Tool Integrations in AI Agents

Identifies security flaws in AI agent tool integrations, covering authentication gaps, input validation failures, and unsafe API connections that expose systems to exploitation.

Mar 18, 2026 • 5 min read

Detecting Prompt Injection and System Prompt Boundaries

Identify prompt injection vulnerabilities in AI systems by probing instruction boundaries, testing context isolation, and detecting system prompt leakage or override weaknesses.

Mar 18, 2026 • 2 min read

Detecting AI Supply Chain and Infrastructure Weaknesses

Identifies vulnerabilities in AI supply chains including model dependencies, training pipelines, third-party components, and infrastructure misconfigurations across AI platforms.

Mar 18, 2026 • 4 min read

Detecting Weak Access Controls on Inference Endpoints

Identify misconfigured AI inference endpoints exposing unauthenticated or over-permissioned access through API probing, header analysis, and permission enumeration techniques.

Mar 18, 2026 • 4 min read

Identifying Exposed MCP Surfaces

Techniques for discovering exposed Model Context Protocol endpoints, authentication gaps, and misconfigured AI platform attack surfaces during reconnaissance.

Mar 18, 2026 • 2 min read

Identifying RAG Pipeline Poisoning Opportunities

Techniques for identifying attack surfaces in RAG pipelines, including document ingestion vectors, embedding manipulation, and retrieval mechanism abuse for security assessment.

Mar 18, 2026 • 4 min read

Vulnerability discovery for AI systems confirms specific weaknesses before moving to exploitation. The goal is to prove a condition is wrong , not just that a surface exists , without yet using it for access or impact. AI vulnerability discovery spans multiple layers: the model's input handling, the retrieval pipeline's access controls, the tool integration's permission scope, and the infrastructure's network exposure.

Many AI vulnerabilities are configuration issues rather than code bugs: a vector database with no authentication, a retrieval endpoint that ignores tenant isolation, an agent granted write access to production systems, or a fine-tuning pipeline that loads models from public registries without verification. These conditions are confirmed through targeted probing that stops short of exploitation, producing evidence of the weakness without triggering the full impact.