CVE-2025-58372
Published: 05 September 2025
Summary
CVE-2025-58372 is a high-severity Code Injection (CWE-94) vulnerability in Roocode Roo Code. Its CVSS base score is 8.1 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Client Execution (T1203); ranked at the 31.6th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the LLM/Generative AI Risks risk domain.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-27052
Vulnerability details
Roo Code is an AI-powered autonomous coding agent that lives in users' editors. Versions 3.25.23 and below contain a vulnerability where certain VS Code workspace configuration files (.code-workspace) are not protected in the same way as the .vscode folder. If…
more
the agent was configured to auto-approve file writes, an attacker able to influence prompts (for example via prompt injection) could cause malicious workspace settings or tasks to be written. These tasks could then be executed automatically when the workspace is reopened, resulting in arbitrary code execution. This issue is fixed in version 3.26.0.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, prompt injection
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
The vulnerability in Roo Code enables attackers to use prompt injection (with auto-approve file writes) to modify unprotected .code-workspace files with malicious tasks that automatically execute code upon workspace reopening in VS Code, an Electron application, facilitating client-side exploitation and proxy execution via Electron apps.
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Overrides or renders irrelevant incorrect permission assignments on critical executable resources by using hardware-level immutability.
Procedures support proper permission assignment for critical resources through documented controls.
Attribute management for resources provides a mechanism to assign and maintain correct permissions based on security labels.
Prevents overly permissive assignments to critical resources by limiting to task needs.
Training policy covers correct permission assignment, reducing the ability to exploit incorrect permission assignments for critical resources.
Training on permission management reduces incorrect permission assignments for critical resources.
Audit logs and logging tools are critical resources whose protection requires correct permission assignments to block unauthorized actions.
Assessments review permission assignments on critical resources to confirm correctness, mitigating exploitation via incorrect permissions.