NVIDIA SIL GEN3C Unauthenticated RCE via Pickle Deserialization in Inference API
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- Code execution
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-502.
Summary
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- Yes
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
No affected products listed by the sources yet.
Remediation
No fixed version listed by the sources yet.
Timeline
- 2026-10-02 Threatist record created from CVE-2026-53805
- 2026-10-03 Alias added: GHSA-478c-rj3v-9229
References
Sources
- CVE-2026-53805 · CVE Program
- CVE-2026-53805 · NVD
- FIRST EPSS
- GHSA-478c-rj3v-9229 · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences