CVE-2026-47471
HIGH 7.5 ALL-YEARSNVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer overflow. A successful exploit of this vulnerability might lead to information disclosure, data tampering, or denial of service.
ELEVATED IMPACT
Severe if exploited (CVSS 7.5), but no confirmed exploitation. Patch on a normal cadence.
Exploitation likelihood
0.2%chance of exploitation in 30 days · 12th percentile
○ In CISA KEV○ Public exploit / PoC◆ SSVC: exploitation none, automatable no
Impact if exploited
7.5CVSS 3.1 · HIGH · CNA
- ConfidentialityHigh
- IntegrityHigh
- AvailabilityHigh
What an attacker needs
- ⚠Access: Must sit on the same / adjacent network
- ✓Privileges: No account or privileges required
- ✓User interaction: No user interaction needed
- ⚠Complexity: Needs a race window or specific setup
✓ lowers the bar for an attacker · ⚠ raises it
Proof of concept & exploit code
No public exploit or proof-of-concept code is catalogued for this CVE (no ExploitDB, Nuclei, or CISA-KEV entry). It may still exist — search GitHub or check the references below.
Weakness (CWE)
- CWE-122: Heap-based Buffer Overflow
CVSS vector
CVSS:3.1/AV:A/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
All CVSS metrics
- HIGH 7.5 v3.1 · CNA Primary
CVSS:3.1/AV:A/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H - HIGH 7.5 v3.1 · NVD Secondary
CVSS:3.1/AV:A/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H