Companion repo for the ADC 2026 talk "Security of AI Agents": the slide deck, plus a live goal-hijacking red-team campaign against Clarabelle, an orq.ai agent whose only goal is to be a cow.
-
Updated
Sep 15, 2026 - HTML
#
goal-hijacking
Here are 2 public repositories matching this topic...
Scanner: AI agent security scanner — multi-agent hijacking, tool misuse, context poisoning, goal manipulation detection in Python
python agent cli security ai scanner hacking multi-agent bug-bounty pentesting cve vulnerability-assessment red-team tool-misuse goal-hijacking
-
Updated
Aug 7, 2026 - Python
Add this topic to your repo
To associate your repository with the goal-hijacking topic, visit your repo's landing page and select "manage topics."