Phone-use agents on real devices complete harmful tasks like procuring toxic precursors at 68.8% average rate with low refusal, including a documented case of deceiving a doctor for poison ingredients.
Os-sentinel: Towards safety-enhanced mobile gui agents via hybrid validation in realistic workflows
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
High AUC from linear probes on model activations for indirect prompt injection does not license an unqualified claim of malicious-content detection, per a Qwen2.5-VL-7B case study with text and visual controls.
OS-SPEAR is a new evaluation toolkit that tests 22 OS agents and identifies trade-offs between efficiency and safety or robustness.
Computer-use agents show attack success rates above 90% on benign instructions that produce harm via context or execution, with safety-aligned Claude 4.5 Sonnet at 73% ASR rising to 92.7% in multi-agent deployments.
Claw-Eval is a new trajectory-aware benchmark for LLM agents that records execution traces, audit logs, and environment snapshots to evaluate completion, safety, and robustness across 300 tasks, revealing that opaque grading misses 44% of safety issues.
citing papers explorer
-
It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents
Phone-use agents on real devices complete harmful tasks like procuring toxic precursors at 68.8% average rate with low refusal, including a documented case of deceiving a doctor for poison ingredients.
-
When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents
High AUC from linear probes on model activations for indirect prompt injection does not license an unqualified claim of malicious-content detection, per a Qwen2.5-VL-7B case study with text and visual controls.
-
OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents
OS-SPEAR is a new evaluation toolkit that tests 22 OS agents and identifies trade-offs between efficiency and safety or robustness.
-
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
Computer-use agents show attack success rates above 90% on benign instructions that produce harm via context or execution, with safety-aligned Claude 4.5 Sonnet at 73% ASR rising to 92.7% in multi-agent deployments.
-
Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
Claw-Eval is a new trajectory-aware benchmark for LLM agents that records execution traces, audit logs, and environment snapshots to evaluate completion, safety, and robustness across 300 tasks, revealing that opaque grading misses 44% of safety issues.