GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

FKIE_CVE-2026-86793

Vulnerability from fkie_nvd - Published: 2026-09-11 12:16 - Updated: 2026-09-11 14:46
Severity
Summary
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.
References
cret@cert.orghttps://github.com/sgl-project/sglang/tree/main
cret@cert.orghttps://vicone.com/blog/cve-2026-86793-sglang-bypass-could-let-attackers-run-code-on-ai-servers/
Impacted products
Vendor Product Version
To clipboard 

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "SGLang",
          "vendor": "SGLang",
          "versions": [
            {
              "lessThanOrEqual": "0.5.18",
              "status": "affected",
              "version": "0",
              "versionType": "custom"
            }
          ]
        }
      ],
      "source": "cret@cert.org"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "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."
    }
  ],
  "id": "CVE-2026-86793",
  "lastModified": "2026-09-11T14:46:12.730",
  "metrics": {},
  "published": "2026-09-11T12:16:52.427",
  "references": [
    {
      "source": "cret@cert.org",
      "url": "https://github.com/sgl-project/sglang/tree/main"
    },
    {
      "source": "cret@cert.org",
      "url": "https://vicone.com/blog/cve-2026-86793-sglang-bypass-could-let-attackers-run-code-on-ai-servers/"
    }
  ],
  "sourceIdentifier": "cret@cert.org",
  "vulnStatus": "Deferred"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Detection rules are retrieved from Rulezet.