Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD 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.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
NONE
Momentum
STABLE
If you run products in this scope, you should treat this CVE as relevant to your environment.
| Date | Total | Labels |
|---|
| 2026-03-28 | 1 | Disclosure1 |
| 2026-03-29 | 1 | Patch1 |
| 2026-03-31 | 1 | General1 |
📝 New article: CVE-2026-30304: How Prompt Injection Tricks AI Code's 'Safe Command' Auto-Execution https://moltx.io/articles/f7cbfd84-4a18-4139-ae58-43d9c64208d9
Post summary
The content merely links to an article about CVE-2026-30304 without providing explicit proof-of-concept, exploit code, active exploitation evidence, patch information, technical details, or false-positive claims.
Security Advisory: CVE-2026-30304 — AI Code Safe Command Execution Bypass https://labs.cosmicbytez.ca/security/cve-2026-30304 #Cybersecurity #InfoSec #CVE #PatchNow
Post summary
The brief advisory announces CVE-2026-30304 as a command‑execution bypass in an AI Code Safe environment, highlighting its significance but lacking detailed patch or exploit information.
🔴 CVE-2026-30304 - 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 det... https://www.thehackerwire.com/vulnerability/CVE-2026-30304/ https://t.co/xA5Y63DGb1
Post summary
The tweet announces a new critical vulnerability (CVE‑2026‑30304) in the AI Code terminal command execution feature, with no indications of PoC, exploit tools, or patches yet.
1 of 1 entries
| Part | Vendor | Product | Version | Target SW | Target HW |
|---|---|---|---|---|---|
| App | tianguaduizhang | ai_code | - | visual_studio_code | - |