APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and business applications. These environments create safety risks that are difficult to capture with attacks placed at a single, known read location. We introduce APEX-Harm, a benchmark for evaluating prompt and script injection against long-horizon agents performing finance, consulting, and legal tasks in large workspaces. Each task contains 115 to 328 files, together with email, calendar, chat, document, spreadsheet, PDF, and code-execution tools exposed through MCP servers. The benchmark includes six attack categories covering static and dynamic in...
| Authors | Ziyi Yang, Adel Bibi, Guohao Li et al. |
|---|---|
| Primary category | cs.CR |
| Published | 9 October 2026 |
| Last updated at source | 9 October 2026 |
Popularity, last 3 days
0 now (-12 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 16 Oct 2026 Topics added cs.CR, cs.CL removed hf-daily-papers, prompt injection, script injection, long-horizon agents, mcp servers, apex-harm, attack success rate, task-specific script replacement
- 16 Oct 2026 Description: Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and business applications. These environments create safety risks that are difficult to capture with → Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and business applications. These environments create safety risks that are difficult to capture with
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.