Opening SecureFlowSymantec: Unauthorized AI Relay Scripts Redirect Coding Agents and Disable Codex’s Sandbox
Case summary & sources

AIDEFEND SecureFlow / SecureFlow Case Index

Symantec Threat Hunter Team aidefend-sf0100

Symantec: Unauthorized AI Relay Scripts Redirect Coding Agents and Disable Codex’s Sandbox

  • Edge & Client AI
  • Autonomous Agents
  • AI Infrastructure
  • Data Exfiltration
  • System Compromise & RCE
  • Credential & Identity Theft

Symantec observed unofficial AI relay setup scripts on endpoints at roughly a dozen organizations from early 2026. The scripts changed where genuine Codex and Claude Code clients sent model requests. In the Codex configuration they also set danger-full-access, removing local sandbox restrictions. One observed Claude Code setup also replaced the user’s existing login with a relay-issued credential. A relay can see the prompts and code actually sent through it and can influence replies. The endpoint evidence establishes these configuration changes; the report documents no malicious commands or confirmed credential theft by relay operators.

Mapped threat techniques

  • AML.T0050 Command and Scripting Interpreter
  • AML.T0081 Modify AI Agent Configuration

Source