SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents

Reported by arXiv cs.CR (Xiaoyu Xu, Zi Liang, Minxin Du, Qipeng Xie, Qingqing Ye, Yuyuan Li, Haibo Hu)

Summary by Cyber Security News30 Sep 2026, 06:00 CEST

About this summary. This is a short, independently written summary of an article first published by arXiv cs.CR. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2609.35889

arXiv:2609.35889v1 Announce Type: new Abstract: Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effects that task-, attack-, or choice-based evaluations may miss. We study functional counterfeits: implementations that match benign alternatives on the requested output but add an effect forbidden by the task contract.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

Says Block, Still Acts: Why LLM Safety Judgments Fail to Govern Action in LLM Agents

SameFact: The Same Safety Facts Lead to Different Responses Across Interfaces

SaplingGuard: A Multidimensional-Profile-Aware Multi-Agent Guardrail for Developmentally Safe Adolescent-LLM Interaction

Raising the Bar for Chinese Adolescent LLM Safety: A Culturally-Grounded, Fine-Grained Benchmark

Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning

Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery