CVE-2026-30306

Prompt Injection Causing Arbitrary Command Execution in SakaDev Visual Studio Code Extension

Published Mar 30, 2026 CVSS 3.1 · 9.8 Critical EPSS < 1% KEV · Not listed
Description
In its design for automatic terminal command execution, SakaDev offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be potentially destructive, it still requires user approval. However, this design is highly susceptible to prompt injection attacks. An attacker can employ a generic template to wrap any malicious command and mislead the model into misclassifying it as a 'safe' command, thereby bypassing the user approval requirement and resulting in arbitrary command execution.

Analysis

AI-generated

Technical impact

SakaDev is a Visual Studio Code extension that automatically runs terminal commands suggested by a language model. The extension classifies commands as safe or potentially destructive, executing safe ones without user confirmation. The design permits prompt injection, allowing an attacker to embed malicious code within a seemingly harmless prompt that misleads the model into labeling the command safe, thereby bypassing the safety check and executing arbitrary shell commands.

Affected Systems

The vulnerability affects the SakaDev extension for Visual Studio Code developed by Rahman Azhar. No specific product versions are listed as fixed, and the published data do not identify which releases are vulnerable, so the impact scope encompasses all installed copies of the extension until a patch becomes available.

Risk and Exploitability

The CVSS score of 9.8 indicates critical severity. The EPSS score of less than 1% suggests that no widespread exploitation has been observed to date, but the high severity means an attacker who can influence the model’s prompt could trigger execution of arbitrary commands. The vulnerability is not listed in the CISA KEV catalog. Attack likely occurs from within the extension’s user interface where the model processes prompts, making it essential to mitigate the issue.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Update the SakaDev extension to the latest patched version as soon as it becomes available.
  • Disable automatic command execution or enforce user confirmation for all commands in the extension’s settings.
  • Monitor the extension’s activity for unexpected command executions.
  • Limit the extension’s permissions to run only the commands that are strictly necessary.
  • Keep Visual Studio Code and its extensions regularly updated.

Generated by OpenCVE AI on April 8, 2026 at 18:23 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Title Prompt Injection Causing Arbitrary Command Execution in SakaDev Visual Studio Code Extension
Type Values Removed Values Added
First Time appeared Rahmanazhar
Rahmanazhar sakadev
CPEs cpe:2.3:a:rahmanazhar:sakadev:*:*:*:*:*:visual_studio_code:*:*
Vendors & Products Rahmanazhar
Rahmanazhar sakadev
Type Values Removed Values Added
First Time appeared Sakadev
Sakadev saka-dev
Vendors & Products Sakadev
Sakadev saka-dev
Type Values Removed Values Added
Title Real-World Prompt Injection Exploiting SakaDev Visual Studio Code Extension for Arbitrary Command Execution
Type Values Removed Values Added
Metrics cvssV3_1

{'score': 9.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'}

ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
Title Real-World Prompt Injection Exploiting SakaDev Visual Studio Code Extension for Arbitrary Command Execution
Weaknesses CWE-94
Type Values Removed Values Added
Description In its design for automatic terminal command execution, SakaDev offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be potentially destructive, it still requires user approval. However, this design is highly susceptible to prompt injection attacks. An attacker can employ a generic template to wrap any malicious command and mislead the model into misclassifying it as a 'safe' command, thereby bypassing the user approval requirement and resulting in arbitrary command execution.
References
Weaknesses
  • CWE-94

    Improper Control of Generation of Code ('Code Injection')

Sources

Status
PUBLISHED
Assigner
mitre
Published
Updated
Apr 1, 2026, 5:57 PM
Reserved
Mar 4, 2026, 12:00 AM
Status
Analyzed
Published
Mar 30, 2026, 9:17 PM
Modified
Jun 17, 2026, 10:32 AM