How to Prompt Inject through Images
Why prompt injecting through images works as a jailbreak, even for GPT 5, and how you can test on your own GPTs.
Jailbreak
4 postsRed-teaming, safety gaps, techniques and mitigation for prompt attacks.
New Jailbreak for GPT-5
It shouldn't be this easy to jailbreak GPT-5, but here we are with a new injection technique.
The Skeleton Key: A New AI Jailbreak Threat
Discover how Skeleton Key AI jailbreak poses new cybersecurity challenges and solutions to mitigate this threat.
Understanding AI Jailbreaks
Explore AI jailbreaks, their risks, and effective strategies to mitigate them in this in-depth analysis.
Subscribe to new posts
Processing your application
Please check your inbox and click the link to confirm your subscription
There was an error sending the email