CVE-2026-53805
CVSS 9.8 CRITICAL: nVIDIA Spatial Intelligence Lab's (SIL) GEN3C contains an unauthenticated remote code execution vulnerability in the… EPSS 0.9% (55th percentile).
Vulnerabilities · 82 days ago
A reachable inference port on a GPU host becomes code execution when the service treats the HTTP body as a Python object. The standard response would focus on patching the bug, but the real break is the trust boundary: any client that can reach the API can make the inference process run attacker code.
VulnCheck says NVIDIA GEN3C's unauthenticated RCE, tracked as CVE-2026-53805, sits in two FastAPI endpoints that pass raw request bodies to `pickle.loads()` with no authentication, validation, or restricted unpickler. The project listens on port 8000 by default and is commonly reached over an SSH tunnel, so the exposed surface is a remote GPU host in lab or cloud deployments; NVIDIA fixed the deserialization path at commit `db2ffe1`, and earlier checkouts remain exposed.
The broader risk is not just this one project. VulnCheck found GEN3C through a GitHub search for public AI/ML code that routes raw request bodies into `pickle.loads()`, which means the same pickle-over-HTTP pattern can recur in other inference services.
CVSS 9.8 CRITICAL: nVIDIA Spatial Intelligence Lab's (SIL) GEN3C contains an unauthenticated remote code execution vulnerability in the… EPSS 0.9% (55th percentile).
1 source covering this story
NVIDIA GEN3C: Unauthenticated RCE via Pickle Deserialization in the Inference API | Blog | VulnCheck
VulnCheck's Initial Access Intelligence team details an unauthenticated remote code execution in NVIDIA's GEN3C, where two FastAPI inference endpoints deserialize raw HTTP request bodies with pickle.loads() with no authentication.
Part of the PlainSec briefing for 2026-06-25