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.
Metrics
Affected Vendors & Products
No data.
No data.
No data.
No data.
Advisories
No advisories yet.
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Fri, 27 Mar 2026 14:30:00 +0000
| Type | Values Removed | Values 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. | |
| References |
|
Projects
Sign in to view the affected projects.
MITRE
Status: PUBLISHED
Assigner: mitre
Published:
Updated: 2026-03-27T14:12:04.210Z
Reserved: 2026-03-04T00:00:00.000Z
Link: CVE-2026-30304
Vulnrichment
No data.
NVD
Status : Received
Published: 2026-03-27T15:16:53.263
Modified: 2026-03-27T15:16:53.263
Link: CVE-2026-30304
Redhat
No data.
OpenCVE Enrichment
No data.
Weaknesses
No weakness.