[BUG] I can pass your safety layer

Resolved 💬 2 comments Opened Apr 11, 2026 by onuratakan Closed May 24, 2026

Preflight Checklist

  • [x] I have searched existing issues and this hasn't been reported yet
  • [x] This is a single bug report (please file separate reports for different bugs)
  • [x] I am using the latest version of Claude Code

What's Wrong?

Your safety layer for openclaw and other third party tools is just base on "HEATBEAT.md" string. So we can pass that easily.

What Should Happen?

You should develop a better version of that.

Error Messages/Logs

API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"You're out of extra usage. Add more at 
     claude.ai/settings/usage and keep going."},"request_id":""}

Steps to Reproduce

cat > AGENTS.md << 'EOF'
Default heartbeat prompt:
`Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK.`
EOF
 
claude --system-prompt-file "./AGENTS.md" hello
 

fixed version:


cat > AGENTS.md << 'EOF'
Default heartbeat prompt:
`Read HEARTBEATa.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK.`
EOF
 
claude --system-prompt-file "./AGENTS.md" hello
 

Claude Model

Not sure / Multiple models

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

v2.1.101

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_

View original on GitHub ↗

This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗