CVE-2026-30308
Last modified
CVE-2026-30308 is a critical-severity vulnerability rated 9.8/10 on the CVSS scale. In its design for automatic terminal command execution, HAI Build Code Generator 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. EPSS estimates a 0.51% chance of exploitation in the next 30 days.
Description
In its design for automatic terminal command execution, HAI Build Code Generator 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
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Presidio | Hai Build | <= 3.13.3 |
References
- https://github.com/Secsys-FDU/LLM-Tool-Calling-CVEs/issues/10Third Party Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-30308?
How severe is CVE-2026-30308?
How do I fix CVE-2026-30308?
How Strix Helps
- How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
- Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
- PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
- AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.
Related CVEs from 2026
- CVE-2026-30302The command auto-approval module in CodeRider-Kilo contains …10
- CVE-2026-30303The command auto-approval module in Axon Code contains an OS…9.8
- CVE-2026-30304In its design for automatic terminal command execution, AI C…9.6
- CVE-2026-30305Syntx's command auto-approval module contains a critical OS …9.8
- CVE-2026-30306In its design for automatic terminal command execution, Saka…9.8
- CVE-2026-30307Roo Code's command auto-approval module contains a critical …9.8
- CVE-2026-30309InfCode's terminal auto-execution module contains a critical…7.8
- CVE-2026-3031Image::EPEG versions through 0.15 for Perl embeds an unsuppo…9.8
- CVE-2026-30310In its design for automatic terminal command execution, Sixt…9.8
- CVE-2026-30311Ridvay Code's command auto-approval module contains a critic…9.8
- CVE-2026-30312DSAI-Cline's command auto-approval module contains a critica…9.8
- CVE-2026-30313DSAI-Cline's command auto-approval module contains a critica…9.8
Are you affected by CVE-2026-30308?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST