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.
CVSS Score
CRITICAL
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Tianguaduizhang | Ai Code | <= 3.12.4 |
Related Weaknesses (CWE)
References
- https://github.com/Secsys-FDU/LLM-Tool-Calling-CVEs/issues/2Issue Tracking
- https://marketplace.visualstudio.com/items?itemName=tianguaduizhang.claude-dev-cProduct
FAQ
What is CVE-2026-30304?
CVE-2026-30304 is a vulnerability with a CVSS score of 9.6 (CRITICAL). 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 th...
How severe is CVE-2026-30304?
CVE-2026-30304 has been rated CRITICAL with a CVSS base score of 9.6/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-30304?
Check the references section above for vendor advisories and patch information. Affected products include: Tianguaduizhang Ai Code.