CVE-2026-30304 Command injection in n/a
Prompt injection allows attackers to bypass safety checks and execute arbitrary commands in AI Code's automatic terminal execution feature.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- A user has to click or open something
- Fix
- None listed
What is CVE-2026-30304?
CVE-2026-30304 is a critical command injection vulnerability in n/a, published on 27 Mar 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Official 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.
Weakness: CWE-20
Which versions are affected by CVE-2026-30304?
It affects 1 product.
Products include Tianguaduizhang Ai Code.
How do I fix CVE-2026-30304?
No fix has been published for CVE-2026-30304 yet. Limit exposure of the affected software until one is available.
Upgrade, and pass arguments to programs as a list instead of through a shell. More about Command injection.
Is CVE-2026-30304 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-30304 exists.
Sources
Also known as GHSA-3vj9-9x9c-pmm5.