In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: zero-initialize GART table on allocation GART TLB is flushed after unmapping but not after mapping. Since amdgpu_bo_create_kernel() does not zero-initialize the buffer, when a single PTE is written the TLB may speculatively load other uninitialized entries from the same cacheline. Those garbage entries can appear valid, and a subsequent write to another PTE in the same cacheline may cause the GPU to use a stale garbage PTE from the TLB. Fix this by calling memset_io() to zero-initialize the GART table with gart_pte_flags immediately after allocation. Using AMDGPU_GEM_CREATE_VRAM_CLEARED, SDMA-based clear will not work since SDMA needs GART to be initialized to work. (cherry picked from commit d9af8263b82b6eaa60c5718e0c6631c5037e4b24)
Casky was already ahead
This CVE exploits attack patterns that Casky's 0matched skills already investigate — long before this vulnerability was disclosed. Claude's reasoning model maps these techniques to MITRE ATT&CK, so practitioners who ran these skills have already seen the threat behaviour in their findings.
CVE-2026-53374 is a memory safety vulnerability in the Linux kernel's AMD GPU (AMDGPU) driver affecting Graphics Address Remapping Table (GART) operations. The vulnerability occurs when GART page table entries (PTEs) are not zero-initialized during buffer allocation, allowing the GPU's TLB (Translation Lookaside Buffer) to speculatively load uninitialized memory entries from the same cacheline. These garbage entries can appear valid to the GPU, potentially enabling unauthorized memory access or information disclosure. This affects systems running the vulnerable Linux kernel versions with AMD GPUs, particularly impacting cloud infrastructure, workstations, and servers leveraging GPU acceleration.
While CVE-2026-53374 carries a CVSS score of 8.8 and currently maps to no specific MITRE ATT&CK techniques or CWE classification, Casky.ai's approach using Claude AI and extended reasoning would identify the attack surface through memory corruption patterns and potential privilege escalation vectors. Practitioners using Casky would observe findings related to uninitialized memory access (CWE-456 equivalent), memory disclosure, and GPU-based side-channel attack patterns. The platform's skill mapping would highlight defensive techniques including memory initialization controls, kernel memory protection mechanisms, and GPU driver hardening practices, enabling security teams to correlate this vulnerability with broader kernel exploitation and data exfiltration attack chains.
Composite risk scoring from EPSS, CISA KEV, Shodan, and GreyNoise — 21 security APIs correlated into a single Casky Risk Score. Coming in Casky Pro. Join early access →
Casky has 0 skills that investigate the attack patterns behind CVE-2026-53374. Run one and get CVSS-scored findings in 3 minutes.
Run the skill that detects this →© 2026 Casky.AI, Inc. · AI Security Investigation