CASEL lowers harmful tool-call trajectories in a controlled agent simulation
Harmful trajectories fell from 14.75 percent to 7.02 percent versus an uncertainty-ranked gate, under equal compute.
Stories per day · 30 days
Relatedagent-security2agentdojo1authorization1casel1injecagent1openclaw1open-weight1prompt-injection1runtime-safeguards1selective-execution1workflow-attack1
4 stories, newest first · one card per story
Stories tagged #tool-using-agents
Low prompt-injection rates mostly mean small agents ignore attacks
Across 33,000 trajectories, 76-80% of failed injections were ignored and only 17-18% were refused.
Approval-token workflow attack bypasses checks on tool-using agents
In local OpenClaw reruns, the original configuration completed the target operation in 8 of 9 cases.
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents
SEAD shows a state-aware defense cutting tool-agent attack success from 48 percent to 4 percent.