Vulnpedia
← All CVEs

CVE-2026-47475

MEDIUM 6.2

Published 2026-07-14 · Last modified 2026-07-15

NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.

NO EXPLOITATION SIGNALS

No known exploitation, public exploit, or elevated probability at this time. Track for changes.

Exploitation likelihood

0.1%chance of exploitation in 30 days · 2nd percentile

○ In CISA KEV ○ Public exploit / PoC

Impact if exploited

6.2CVSS 3.1 · MEDIUM

  • ConfidentialityNone
  • IntegrityNone
  • AvailabilityHigh

What an attacker needs

  • ⚠Access: Requires local access to the host
  • ✓Privileges: No account or privileges required
  • ✓User interaction: No user interaction needed
  • ✓Complexity: No special conditions — reliably repeatable

✓ lowers the bar for an attacker · ⚠ raises it

Proof of concept & exploit code

Test against your own equipment

curl -s https://vulnpedia.com/cve/CVE-2026-47475/poc.jsonMachine-readable PoC index for this CVE (for automation).

Listed for defensive triage, patch verification, and authorized testing on systems you own. Machine-readable: /cve/CVE-2026-47475/poc.json

Affected

Vendors Nvidia

Products Tensorrt Llm

Weakness (CWE)

  • CWE-617: Reachable Assertion

CVSS vector

CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

All CVSS metrics

  • MEDIUM 6.2 v3.1 · CNA Primary
    CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
  • MEDIUM 6.2 v3.1 · NVD Secondary
    CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

Technical & other

Sources: NVD · CVE.org · EPSS