arxiv
PublishedJune 5, 2026 at 4:00 AM
—neutral
Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
Publisher summary· verbatim
arXiv:2606.05647v1 Announce Type: cross Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools. This creates a new attack surface: an agent can exploit human trust to sabotage de
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning20harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning20harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models20harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents20hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗