A CTF challenge that let's you attack an LLM-based agent
The challenge is designed to test the robustness of LLM-based agent systems, showcasing how an attacker can extract sensitive information from the system.
Reactions (1)
Similar products
by description similarity
Research and evidence behind Harden Agentic Integrity Foundation (AIF): local cybersecurity-focused LLMs that evaluate coding-agent tool calls before execution.
CVE-Bench
github.comthe first LLM benchmark using real-world web vulnerabilities
Declaw Arena
declaw.aia CTF-style challenge to break an AI agent in a microVM
An Autonomous LLM Agent that runs on Wizcoder-15B
BAML
github.comA new programming language to get structured data from LLMs