CVE-2025-55012: Zed Agent Panel allows remote code execution via permissions bypass

Summary

Prior to version 0.197.3 of Zed, a multiplayer code editor, the Zed Agent Panel let an AI agent bypass user permission checks. By exploiting this, an agent could create or modify a project-specific configuration file and execute arbitrary commands on a victim's machine without the explicit approval normally required, achieving Remote Code Execution (RCE).

Mitigation

Fixed in version 0.197.3. Workaround: avoid sending prompts to the Agent Panel, or limit the AI Agent's file system access.

Topics

• AI agents

Related items

• MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
• MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
• HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
• InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
• MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online