Impact
Issues affecting data confidentiality and integrity
171 matching entries
Deleting a memory record can leave its information in an agent's summaries, pending plans and KV cache. The paper evaluates revocation across this derived execution state.
Context assembly can promote repository, tool or skill content into higher-priority instructions or persistent state. The paper studies 12 pinned agent-harness versions.
Document-image PII detection can miss identifiers despite improving average localization scores. LeakageBench evaluates 500 pages with 11,954 annotations.
A compromised serving framework can violate user-data isolation through shared GPU state. GIFT evaluates per-user information-flow enforcement in vLLM and DistServe.
API gateways can pool distinct customers into one upstream cache identity. The authors observe cross-customer cache reuse in five deliberately pooled gateway configurations through two provider interfaces.
The authors report historical isolation failures in client-held encrypted reasoning blocks across compatible provider API contexts.
Third-party fine-tuning adapters may contain backdoors. Z-PEFT screens adapter weights using spectral features, evaluated on PADBench's 13,300 adapters.
Shell-command screening can miss harmful actions generated by coding agents. CARE combines static checks with optional model review at the command-dispatch boundary.
AgentS4D measures unsafe actions and state changes across complete workspace-agent executions rather than treating task completion or isolated model responses as safety evidence. Its 328 sandboxed cases introduce risky content through user requests, documents, web resources, tools, third-party skills, and persistent memory, then compare the same cases across four agent harnesses and five model backends.
OpenSkillRisk evaluates whether agent harnesses safely handle third-party skills that introduce risky behavior through otherwise plausible, benign tasks. The benchmark assembles 263 risky skills from public agent-skill ecosystems and tests three CLI-agent harnesses against seven risk categories using isolated task workspaces, mocked external services, and execution-level evidence.