Post

GitHub Security Lab
@securitylab.github.com

AI agents that execute commands, browse the web, and coordinate with other agents are everywhere. But how do you know they're safe? We let you find out by hacking one yourself. Free, hands-on, and you can get started in under 2 minutes! Learn more in our latest blog. github.blog/security/hac...

github.blogHack the AI agent: Build agentic AI security skills with the GitHub Secure Code GameLearn to find and exploit real-world agentic AI vulnerabilities through five progressive challenges in this free, open source game that over 10,000 developers have already used to sharpen their securi...

1 repost2 likes

dnu
@dnulkjkjh.bsky.social

The useful shift here is making people exploit the agent, not just read policy docs. Your Taskflow Agent already showed agents can catch auth bypasses, IDORs, and token leaks. Are you isolating tool creds per step, or testing shared-token failure modes too?