0.0
NA
CVE-2026-30304
AI Code Command Injection Vulnerability
Description

In its design for automatic terminal command execution, AI Code 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.

INFO

Published Date :

March 27, 2026, 3:16 p.m.

Last Modified :

March 27, 2026, 3:16 p.m.

Remotely Exploit :

No
Affected Products

The following products are affected by CVE-2026-30304 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

No affected product recoded yet

Solution
Prevent prompt injection by validating all commands before execution.
  • Only execute commands confirmed safe by the model.
  • Require user approval for all commands.
  • Implement strict input validation for commands.
  • Update AI model to detect malicious prompts.
References to Advisories, Solutions, and Tools

Here, you will find a curated list of external links that provide in-depth information, practical solutions, and valuable tools related to CVE-2026-30304.

URL Resource
https://github.com/Secsys-FDU/LLM-Tool-Calling-CVEs/issues/2
https://marketplace.visualstudio.com/items?itemName=tianguaduizhang.claude-dev-china
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-30304 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-30304 weaknesses.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-30304 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-30304 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • New CVE Received by [email protected]

    Mar. 27, 2026

    Action Type Old Value New Value
    Added Description In its design for automatic terminal command execution, AI Code 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.
    Added Reference https://github.com/Secsys-FDU/LLM-Tool-Calling-CVEs/issues/2
    Added Reference https://marketplace.visualstudio.com/items?itemName=tianguaduizhang.claude-dev-china
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.