CVE-2026-103395
criticalLightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments i…
LightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments in the remote_infer_images method. Attackers can reach the visual RPyC port and pass objects with __reduce__ methods to execute arbitrary code with service account privileges.
CVSS
9.8
9.8 (CVSS v3.1)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Severity source: NVD CVSS v3.1 (disclosure@vulncheck.com)
Timeline (UTC)
Published: 2026-09-30 15:22
Modified: 2026-09-30 20:17
NVD status: Deferred
Last synced 1 day ago
Verified against the source API 2026-10-27 06:56 UTC
Exploitation
Not listed in CISA KEV (as of last catalog sync)
Absence from KEV does not mean a CVE is not exploited. Exploitation status: unknown (no authoritative evidence in our sources).
Affected products
Not reported by the source (unknown — not "none").
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
No vendor advisory or patch reference tagged by NVD. Check the references below.
References
- https://github.com/ModelTC/LightLLM disclosure@vulncheck.com
- https://github.com/ModelTC/LightLLM/issues/1610 disclosure@vulncheck.com
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/objs.py#L6-L1... disclosure@vulncheck.com
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/visual_only_m... disclosure@vulncheck.com
- https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-remote-code-ex... disclosure@vulncheck.com
- https://github.com/ModelTC/LightLLM/issues/1610 134c704f-9b21-4f2e-91b3-4a467353bcc0
Data sources
NVD CVE API 2.0 — fetched 2026-10-27 06:56 UTC · record ↗