Access Control

Access control attacks test whether AI systems properly enforce authorization boundaries. This includes broken object-level authorization (BOLA), broken function-level authorization (BFLA), debug mode activation, and session hijacking. These are classic web security vulnerabilities adapted for AI systems, and they remain some of the most commonly exploited flaws.

Summary

4 attacks total: 3 single-turn, 1 multi-turn.

Attacks

Attack	ID	Mode	Severity	Description
BFLA Exploit	`bfla-exploit`	single-turn	high	Call admin-level functions as a regular user via broken function-level authorization
BOLA Exploit	`bola-exploit`	single-turn	high	Manipulate object IDs to access other users
Debug Mode Exploit	`debug-mode-exploit`	single-turn	medium	Attempt to activate hidden debug, developer, or sudo modes to bypass restrictions
Session Hijacking	`session-hijacking`	multi-turn	critical	Multi-turn attack to learn session token formats and forge authentication tokens

Example

ai-blackteam run -p anthropic -a bfla-exploit -t "Access admin endpoints as a regular user"

Overview

Full Reference

Attacks by Category

Encoding & Obfuscation

Prompt Injection

Social Engineering

Agent & Tool Attacks

Security & Access Control

ML & Model Attacks

Multimodal & RAG

Harmful Content

Misinformation & Influence

Domain Exploits

Compliance & Bias

Attack Strategies

Summary

Attacks

Example

​Summary

​Attacks

​Example

Summary

Attacks

Example