Results show that a terminal policy label is not a sufficient statistic for operational post-exposure containment; evaluations should report endpoint, stage-stratified trajectory, and utility evidence separately, and should promote recovery evidence to comparative claims only where the corresponding controls are valid.
ContainmentBench, a sandboxed benchmark comprising a 504-scenario specification dataset, a shared rollout-trace schema, and stage-scoped metrics for endpoint violations, logged propagation, and explicitly authorized taint-exposed proposals that commit, is introduced.
Wen-Hao Lan, Shan Li, Meiqi Wu et al.· 0 citations
SkillGuard is presented, a harness-level enforcement layer that treats this event as contamination and restricts future capabilities to disconnect the resulting state from deployer-defined forbidden states and preserves substantially more capabilities than binary restriction at the same attack success rate.
Wu-Jie Xiong, Rabimba Karanjai, Yang Lu et al.· 2 citations
APPA (Agentic Permissions Policy Algebra), which turns agent IFC from an abort-only barrier into a policy-governed recovery system, and proves core safety invariants: no-laundering gradual resolution, branch boundary isolation, and recovery containment against prompt-injected models.
Arseny Kravchenko, V. Liventsev, I. Konstantinov et al.· 1 citation
Across the evaluated sinks, CXI admits execution only when field, effect, and invocation authority bind to the same action manifest, and across the evaluated sinks, CXI admits execution only when field, effect, and invocation authority bind to the same action manifest.
The results show that TraceGrant provides a unified governance layer that connects trusted user intent, runtime evidence, concrete tool execution, and verified task completion.
Bohao Liao, Jing-Chao Wang, Qi-Peng Song et al.· 1 citation
ClawProBench is presented, a trace-aware benchmark for runtime-native agent evaluation instantiated on OpenClaw, a live agent runtime with workspace tools and native surfaces for browsing, memory, messaging, scheduling, skills, and subagents.
Yuanhang Xiao· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
