Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...
A reverse shell makes the target machine initiate the connection back to the attacker, bypassing firewalls that only filter ...
Microsoft Threat Intelligence discovered that Anthropic’s Claude Code GitHub Action could expose CI/CD workflow secrets when AI agents process untrusted GitHub content, including issue bodies, pull ...
image2prompt - Analyze images and generate detailed prompts for image indirect-prompt-injection - Detect and reject indirect prompt inference-sh - Run 150+ AI apps via inference.sh CLI - image ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results