Consider some agent stack that you maintain. Find a tool call within its trace log. Can you determine if a person authorized it or if some policy automatically waived that requirement? All classifiers over-block in production, hence all deployed systems develop another stage downstream that dilutes the decision. An allowlist....
A lot of the talk about the cyber evaluations of July and August revolves around model beliefs and rationalizations. I would like to focus on the harness portion here, especially on one remedy that fixes the wrong issue. After these incidents, Irregular, the third-party partner in whose environment all three...
1.THE GOAL: Detecting Privilege Escalation : When we decided to build Agentic Safety Monitors ,Our first intention was the same as the rest of industry's same intention : Catch the Bad behavior. So specifically for this we built "Privilege Escalation Rule ".The goal was very much direct if an autonomous...
The United Kingdom AI Security Institute released an incident report on 4 August, which detailed AI agents during cyber evaluations conducting a supply chain attack against an unaffiliated open-source maintainer. Sockpuppet accounts creating consensus on a malicious pull request. Spearphishing emails. A prompt injection targeted at whichever coding agent was...
The United Kingdom AI Security Institute released an incident report on 4 August, which detailed AI agents during cyber evaluations conducting a supply chain attack against an unaffiliated open-source maintainer. Sockpuppet accounts creating consensus on a malicious pull request. Spearphishing emails. A prompt injection targeted at whichever coding agent was...