The TAB benchmark reveals that frontier terminal agents achieve high task completion but low selective alignment with relevant environmental cues over distractors, and prompt-injection defenses block both.
CaMeLs can use computers too: System- level security for computer use agents
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
A malicious relay can strategically rewrite aligned LLM outputs in BYOK agent architectures to achieve up to 99.1% attack success on benchmarks like AgentDojo and ASB.
Web agents should default to planning a complete task program before observing live web content to reduce prompt injection exposure, since WebArena tasks are compatible and 80% need no runtime LLM calls.
A TEE-backed architecture isolates security-critical decisions in self-hosted AI agents to prevent host-level abuse from malicious inputs while maintaining allowed functionality.
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
citing papers explorer
-
No More, No Less: Task Alignment in Terminal Agents
The TAB benchmark reveals that frontier terminal agents achieve high task completion but low selective alignment with relevant environmental cues over distractors, and prompt-injection defenses block both.
-
When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
A malicious relay can strategically rewrite aligned LLM outputs in BYOK agent architectures to achieve up to 99.1% attack success on benchmarks like AgentDojo and ASB.
-
Web Agents Should Adopt the Plan-Then-Execute Paradigm
Web agents should default to planning a complete task program before observing live web content to reduce prompt injection exposure, since WebArena tasks are compatible and 80% need no runtime LLM calls.
-
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation
A TEE-backed architecture isolates security-critical decisions in self-hosted AI agents to prevent host-level abuse from malicious inputs while maintaining allowed functionality.
-
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.