Skip to main content
cvebuzz

CVE mentions, exploit signals, and PoC evidence in one fast public view.

CVE detail

CVE-2026-5760

SGLang's reranking endpoint (/v1/rerank) achieves Remote Code Execution (RCE) when a model file containing a malcious tokenizer.chat_template is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment().

CVSS 9.8 · CriticalBuzz score 28.41 public exploit repository references

Buzz score

Why this CVE is surfacing

Buzz score total 28.4

This all-time snapshot uses the same composite formula as Trending across a 30-year evidence window, rather than a current rolling window.

Buzz score components · mention 13.9 · diversity 10.0 · KEV 0.0 · OTX 0.0 · PoC 4.5
Mention score
13.9
3 evidence mentions in the snapshot
Diversity score
10.0
2 sources across 2 categories
KEV score
0.0
No KEV entry observed
OTX score
0.0
0 OTX pulses
PoC score
4.5
1 repos · best confidence 0.90
Best PoC traction
0
Maximum stars on a matched PoC repo

Why it matters now

Mention timeline

Total mentions
0
within the 30d window
Peak daily
0
highest bucket

Evidence

Source links by recency

Newest mentions first
3 source links · newest first

Exploit code

Public exploit repository references

Public PoC repositories are third-party, potentially unsafe artifacts. Treat their code as untrusted and use it only on authorized systems in an isolated, least-privilege environment. cvebuzz does not execute the code or verify that an exploit works.

1 repository references · best confidence 0.90 · max 0 stars
  • Stuub/SGLang-0.5.9-RCEHigh confidence
    githubNVD Exploit reference0 starsDiscovered Jul 19, 2026, 12:20 AM

    NVD labels the source link as Exploit; this is not independent verification of the repository's code.

Related records

Similar CVEs

6 related CVEs with shared weakness or product evidence
  • CVE-2026-12946

    IBM Langflow OSS 1.0.0 through 1.10.0 could allow a remote attacker to inject arbitrary code on the system, due to the improper control of user input code.

    CVSS 9.9 · Critical
    1 mention
  • CVE-2026-61536

    Banks generates meaningful LLM prompts using a simple template language. In versions prior to 2.4.3, banks parses Tool JSON objects from the rendered body of {% completion %} bloc…

    CVSS 7.5 · High
    1 mention
  • CVE-2026-18245

    Improper control of code generation in Amazon @aws-amplify/codegen-ui-react before 2.20.6 might allow a remote authenticated user to execute arbitrary code in end-user browsers, d…

    CVSS 6.4 · Medium
    3 mentions
  • CVE-2026-13435

    IBM Langflow OSS 1.0.0 through 1.10.1 contains an improper input validation vulnerability in the PythonREPL sandbox implementation.

    CVSS 9.9 · Critical
    1 mention
  • CVE-2026-14602

    The Remote API WordPress plugin through 0.2 does not authenticate a request before deserializing user-supplied input, allowing unauthenticated attackers to inject arbitrary PHP ob…

    CVSS 9.0 · Critical
    1 mention
  • CVE-2026-17922

    Inappropriate implementation in Enterprise in Google Chrome prior to 151.0.7922.72 allowed a remote attacker to execute arbitrary code via a crafted HTML page. (Chromium security…

    CVSS 8.8 · High
    2 mentions