THREATOPS
THREAT OPS › Threat News › [NVD] CVE-2026-30304 (CRITICAL 9.6) — 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

[NVD] CVE-2026-30304 (CRITICAL 9.6) — 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

lownvdPublished 2026-03-27

CVE-2026-30304 CVSS: 9.6 CRITICAL Published: 2026-03-27T15:16:53.263

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 r

Indicators of compromise

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-30304