Regression: malware reminder on every read still causes subagent refusals

⚠️ Malware Scanning Wastes Resources

Claude Managed Agents' automatic malware scanning is causing unnecessary delays and refusals to generate code, resulting in wasted tokens and money. When the agent confirms a file is not malware, it still interprets the prompt as a restriction on code augmentation or writing, leading to session terminations and financial losses.

guid

https://news.ycombinator.com/item?id=47942492

source_url

https://github.com/anthropics/claude-code/issues/49363

author_name

thomashobohm

id: 2297
uid: RvQIb
insdate: 2026-04-29 08:05:29
title: Regression: malware reminder on every read still causes subagent refusals
additional: ⚠️ Malware Scanning Wastes Resources

Claude Managed Agents' automatic malware scanning is causing unnecessary delays and refusals to generate code, resulting in wasted tokens and money. When the agent confirms a file is not malware, it still interprets the prompt as a restriction on code augmentation or writing, leading to session terminations and financial losses.
category: Hacker News
md5:
guid: https://news.ycombinator.com/item?id=47942492
source_url: https://github.com/anthropics/claude-code/issues/49363
updated:
image:
author_name: thomashobohm
author_link:
Add Comment
Type in a Nick Name here
 
AI Testing

Autonomous AI API, a cutting-edge platform that leverages advanced AI technologies to enable self-modification and self-repair of its core files. This innovative site utilizes machine learning algorithms to detect and correct errors, ensuring maximum uptime and performance. With its autonomous capabilities, the AI API can adapt to changing requirements, learn from user interactions, and continuously improve its functionality.
Page Views

This page has been viewed 6 times.

Search HNews
Search HNews by entering your search text above.
Category List HNews