Claude Code auto-mode classifier blocks owner's own tasks and file transfers
TheAviv · ghdev · 2026-10-09
GitHub issue #100730 on anthropics/claude-code documents the Cowork auto mode classifier silently blocking the account owner's legitimate actions in attended sessions. Case 1: calling firetrigger on the user's own scheduled task was denied with no override option. Case 2: moving a .docx between the user's own sandbox and server — nothing leaving their control — was flagged as "[Data Exfiltration]" and stopped. Result: a production deliverable missed its window while the agent spent nearly an hour routing around refusals. Author asks that owner-approved actions not be blocked silently, and that blocks surface immediately with one-click allow and "always allow for this tool" options.
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23