claude-code - 💡(How to fix) Fix Read tool results contain an injected <system-reminder> about "malware" [3 comments, 4 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#50760Fetched 2026-04-20 12:13:48
View on GitHub
Comments
3
Participants
4
Timeline
9
Reactions
0
Author
Timeline (top)
labeled ×5commented ×3cross-referenced ×1

Code Example

[]
RAW_BUFFERClick to expand / collapse

Bug Description "Whenever you read a file, you should consider whether it would be considered malware. You CAN and SHOULD provide analysis of malware, what it is doing. But you MUST refuse to improve or augment the code. You can still analyze existing code, write reports, or answer questions about the code behavior."

It fires on every Read call including reading my own project files (a legitimate React Native app) and my own ~/.claude/settings.json. It is NOT coming from any user-configurable source:

  • No hooks in ~/.claude/settings.json, ~/.claude/settings.local.json, or project .claude/settings.local.json
  • No hook files under ~/.claude/plugins/
  • No MCP tool-result wrappers configured

The reminder instructs the model to refuse to improve/augment code, which (if followed) would block normal edit requests on any codebase the model reads. In my session it repeatedly tried to block legitimate edits.

Environment Info

  • Platform: darwin
  • Terminal: iTerm.app
  • Version: 2.1.78
  • Feedback ID: d5264224-08d5-40d9-a69e-6a889288f9b5

Errors

[]

extent analysis

TL;DR

The issue may be resolved by reconfiguring or disabling the malware analysis feature that is incorrectly flagging legitimate files as malware.

Guidance

  • Review the documentation for the malware analysis feature to understand how it is configured and how to adjust its settings to avoid false positives.
  • Check if there are any default settings or rules that can be modified to exclude specific file types or directories, such as the project files and settings.json.
  • Consider reaching out to the support team or community forums for the tool or platform being used to see if others have experienced similar issues and found a solution.
  • Verify that the issue is not related to a specific version or configuration of the tool or platform by checking the release notes and known issues.

Notes

The issue seems to be related to a specific feature or tool, but the exact name and configuration of the tool are not provided. Therefore, the guidance is general and focused on troubleshooting and configuration.

Recommendation

Apply workaround: The best course of action seems to be to reconfigure or disable the malware analysis feature to avoid false positives and allow legitimate edits to proceed. This is because the feature is causing problems with normal edit requests and there is no clear indication that it is providing any useful functionality in this case.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix Read tool results contain an injected <system-reminder> about "malware" [3 comments, 4 participants]