AI security incident: VU#665416: SGLang (sglang) is vulnerable to code execution attacks via unsafe pickle...
Overview Two unsafe pickle deserialization vulnerabilities have been discovered in the SGLang open-source project, one within the tool's multimodal generation module and another within the Encoder Parallel Disaggregation system. SGLang is a serving framework for large language models (LLMs) and multimodal models.
Why This Is AI-Related
This advisory is part of the public incident archive, but the current source material uses limited explicit AI terminology, so the cited sources should be reviewed carefully when judging AI relevance and exposure.
- Explicit AI-specific signals are limited in the current source material, so use the cited advisory to validate scope during triage.
Affected Workflow
Model registries, artifact scanners, notebook workflows, and CI/CD steps that handle model files need immediate review.
Likely Attack Path
The malicious payload is embedded in model artifacts or serialized objects, then executes or bypasses scanning during load and inspection.
Impact
The advisory affects model artifacts or serialized AI assets, which can bypass inspection or execute during load and validation steps. Severity HIGH. Classification confidence 99%. Source channel RSS.
Detection And Triage Signals
- New or unsigned model artifacts entering the registry
- Scanner output gaps for pickle or custom model formats
- Unexpected code paths during model loading or validation jobs
Recommended Response
- Inventory model artifacts, serialized objects, and scanners that touch the affected package or workflow.
- Block untrusted model files and revalidate registry, CI, or notebook loading paths before restoring normal operation.
- Review artifact provenance, scanner output, and recent model-ingestion activity for suspicious changes.
Compliance And Business Impact
Model artifact compromise undermines trust in the training and deployment chain and can create stealthy persistence in ML workflows.
Sources
Want alerts like this in real time?
Get notified with incident context, likely impact, and response guidance.
Get Notified