Arbitrary command execution via prompt-injection misclassification
Published Mar 27, 2026 · Updated Mar 27, 2026
Prompt injection in AI Code 3.12.4 and earlier allows remote attackers to execute arbitrary terminal commands via a crafted prompt. The Tool Call Parser, Command Validation Logic, and Auto-Execution Module accept the model's safe classification for a wrapped malicious command and skip required approval. Exploitation requires user interaction and selection of Execute safe commands; successful commands execute in the local terminal context.
Summary
What happened
Prompt injection in AI Code 3.12.4 and earlier allows remote attackers to execute arbitrary terminal commands via a crafted prompt. The Tool Call Parser, Command Validation Logic, and Auto-Execution Module accept the model's safe classification for a wrapped malicious command and skip required approval. Exploitation requires user interaction and selection of Execute safe commands; successful commands execute in the local terminal context.
The record
- CVE
- CVE-2026-30304
- Published
- Mar 27, 2026
- Updated
- Mar 27, 2026
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-20, T1059
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 27, 2026CVE publishedPublication date reported by the CVE source.
- Mar 27, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo