CVE-2026-30304
In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands.
Published Mar 27, 2026 · updated Jun 17, 2026 · tianguaduizhang ai code
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.
Code
The project this record applies to. Exploit listings stay in References.
Timeline
Detection, updates, and resolution for this record.
Mar 27, 2026 · NIST NVD
Detected
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 p
Jun 17, 2026 · NIST NVD
Updated
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 p
Affected
- cpe tianguaduizhang/ai codeversion unspecified
Sources
- CVE.orgVulnerability recordCVE-2026-30304
Official CVE identifier
cve.org - NIST NVDVulnerability recordCVE-2026-30304
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
nvd.nist.gov