CVE-2026-65104High· 7.1▾ TwilightNVIDIA Megatron-LM for all platforms contains a vulnerability in inference, where an attacker could cause hash collisions in the cache used for inference requests. A successful exploit of this vulnerability might lead to data tampering a…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 39.1 · likelihood 0 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Exploit-prediction probability, daily snapshots since Oct 15.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
0.1%
NVIDIA Megatron-LM for all platforms contains a vulnerability in inference, where an attacker could cause hash collisions in the cache used for inference requests. A successful exploit of this vulnerability might lead to data tampering and partial information disclosure.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-65180High· 7.8NVIDIA Megatron-LM contains a vulnerability in checkpoint loading where an Attacker may cause an RCE by convincing a user to load a maliciously crafted file
CVE-2026-65110High· 7.8NVIDIA Megatron-LM contains a vulnerability in checkpoint loading where, an attacker could cause an RCE by convincing a user to load a maliciously crafted file
CVE-2026-47486High· 7.8NVIDIA PhysX for all platforms contains a vulnerability where an attacker could cause an out-of-bounds write
CVE-2026-65145Critical· 10.0NVIDIA NeMo Agent Toolkit contains a vulnerability where a attacker could cause a missing authentication issue
CVE-2026-65151High· 8.4NVIDIA NeMo Agent Toolkit contains vulnerability where an attacker could cause a SQL injection issue
CVE-2026-65119High· 8.4NVIDIA TensorRT-LLM for any platform contains a vulnerability in KvCacheAwareRouter tokenizer loading, where an attacker could cause inclusion of functionality from an untrusted control sphere