NVIDIA SIL GEN3C Unauthenticated RCE via Pickle Deserialization in Inference API
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| nv-tlabs | GEN3C | affected |
|
No data.
No data.
| Vendor | Product | Versions | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Nv-tlabs | Gen3c |
|
No CVSS v3.0
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: < 1% (0.872% probability within 30 days)
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Nv-tlabs
Nv-tlabs gen3c |
|
| Vendors & Products |
Nv-tlabs
Nv-tlabs gen3c |
| 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
|