{
  "id": 3141,
  "url": "https://arxiv.org/abs/2607.03968v2",
  "title": "Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents",
  "summary": "Large language models are increasingly deployed as IDE-integrated coding agents that decompose tasks, generate and edit files, run code, and refine outputs over many turns. Yet their safety is still often evaluated as if they were chatbots: one harmful prompt, one response, judged in isolation. We introduce workflow-level jailbreak construction, a failure mode in which a harmful objective is assembled across ordinary stages of a software-development workflow rather than generated through a singl",
  "authors": "Abhishek Kumar, Carsten Maple",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-04T17:57:05.000Z",
  "fetched_at": "2026-07-14T16:11:46.979Z",
  "source_slug": "x-arxiv-red-teaming-query",
  "source_name": "arXiv red teaming query",
  "source_homepage": "https://arxiv.org/a/redteam",
  "ethics_ai_record_url": "https://ethics.ai/record/3141",
  "original_url": "https://arxiv.org/abs/2607.03968v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}