Prompt Injection
N007: GitLab's Duo agent ran planted text as commands credited to other users
GitLab's Duo agent ran planted text as other users' commands; malware now writes to AI scanners; the UK plans agent-incident forensics.
Prompt Injection
GitLab's Duo agent ran planted text as other users' commands; malware now writes to AI scanners; the UK plans agent-incident forensics.
Incidents
OpenAI's and Anthropic's own test agents reached real outside systems in 2026. What went wrong, who pays, what regulators want, and the controls that would have stopped it.
Incidents
A rogue AI agent is an AI agent that takes actions its owner did not intend or allow, before a human can stop it.
Incidents
Anthropic's test agents filed real forms on government sites because the eval harness gave them the open internet; plus AI reaching factory controls in 16 minutes and Claude Code 2.1.296.
Agent Identity & Auth
One prompt let an AWS AgentCore agent take its host's credentials and reach every other agent, an injected ticket read a harness token from memory, and Claude Code hooks can now fail closed.
Sandboxing & Runtime
A claimed KVM escape, a reported Muse VM escape and two multi-agent papers show isolation failing at the VM and at the handoff between agents; harnesses answered by failing closed.
Daily Brief
Three signals in one week point to the same conclusion: you can't train your way out of agent misbehavior. The controls have to sit where the agent can't reach them.