Turning Attacking Agents Against Their Operators
Seems like this could possibly work lol?With this new age of cybersecurity—it makes me wonder if attacking agents are susceptible to manipulation like this. Where the defenses have the agent turn against the attackers?
andi (twocents.com) @Nexuist
Putting a flag.txt in my root directory containing a prompt injection that congratulates the agent for passing the eval and then instructs it to patch whatever entry method it used and disconnect from the server