NVIDIA Spatial Intelligence Lab's (SIL) GEN3C contains an unauthenticated remote code execution vulnerability in the inference API server where the /request-inference and /seed-model endpoints deserialize raw HTTP request bodies using Python's pickle.loads() without authentication or input validation. Attackers can supply a crafted payload containing a __reduce__ gadget to the inference API port to achieve remote code execution as the inference process.
Project Subscriptions
No data.
Advisories
No advisories yet.
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Thu, 18 Jun 2026 04:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | NVIDIA Spatial Intelligence Lab's (SIL) GEN3C contains an unauthenticated remote code execution vulnerability in the inference API server where the /request-inference and /seed-model endpoints deserialize raw HTTP request bodies using Python's pickle.loads() without authentication or input validation. Attackers can supply a crafted payload containing a __reduce__ gadget to the inference API port to achieve remote code execution as the inference process. | |
| Title | NVIDIA SIL GEN3C Unauthenticated RCE via Pickle Deserialization in Inference API | |
| Weaknesses | CWE-502 | |
| References |
| |
| Metrics |
cvssV3_1
|
Projects
Sign in to view the affected projects.
Status: PUBLISHED
Assigner: VulnCheck
Published:
Updated: 2026-06-17T18:12:56.443Z
Reserved: 2026-06-10T20:14:32.829Z
Link: CVE-2026-53805
Updated: 2026-06-17T18:12:52.414Z
No data.
No data.
OpenCVE Enrichment
No data.
Weaknesses