InjectionWeakness · CWE-74

CVE-2026-7669

MEDIUM · 5.6 CVSS v3.1 Published 2026-05-02
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
65/100
Remediation priority · Elevated
Remotely reachable No privileges Zero-click

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function get_tokenizer of the file python/sglang/srt/utils/hf_transformers_utils.py of the component HuggingFace Transformer Handler. The manipulation of the argument trust_remote_code with the input False as part of Boolean results in code injection. The attack can be executed remotely. A high complexity level is associated with this attack. The exploitability is considered difficult. In get_tokenizer(), when the caller passes trust_remote_code=False and HuggingFace transformers v5 returns a TokenizersBackend instance (the generic fallback for tokenizer classes not in the registry), SGLang silently re-invokes AutoTokenizer.from_pretrained with trust_remote_code=True, overriding the caller's explicit security setting. A model repository containing a malicious tokenizer.py referenced via auto_map in tokenizer_config.json will execute arbitrary Python in the SGLang process during this second call. No log line or warning is emitted. The override affects all current SGLang versions because transformers==5.3.0 is pinned in pyproject.toml. Both tokenizer_mode="auto" and tokenizer_mode="slow" are affected. The exploit is now public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

In SGLang's get_tokenizer() function, when HuggingFace transformers v5 returns a TokenizersBackend fallback instance (for unregistered tokenizer classes), the code silently re-invokes AutoTokenizer.from_pretrained with trust_remote_code=True, overriding the caller's explicit False setting. This allows a malicious model repository with a crafted tokenizer.py in tokenizer_config.json to achieve arbitrary code execution in the SGLang process.

MitigationModify get_tokenizer() to respect the caller's trust_remote_code=False setting instead of overriding it; do not silently re-invoke with trust_remote_code=True. Alternatively, log a warning and refuse to load the tokenizer rather than bypass the security setting.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
High
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
Low
Integrity
Low
Availability
Low

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify SGLang installation
    Run 'pip show sglang' or 'python -c "import sglang; print(sglang.__file__)"' to locate the SGLang package installation
    Affected if SGLang is installed and the vulnerable get_tokenizer() function exists in the codebase
  2. Locate the get_tokenizer function source
    Find the file containing get_tokenizer() in the SGLang package, typically in the sglang python package directory
    Affected if The function is found and can be inspected for the vulnerable code pattern
  3. Inspect get_tokenizer for trust_remote_code override
    Open the get_tokenizer source file and search for code that re-invokes AutoTokenizer.from_pretrained with trust_remote_code=True after receiving a TokenizersBackend fallback
    Affected if The code explicitly sets trust_remote_code=True when loading a fallback tokenizer, overriding the caller's False setting
  4. Check if tokenizer loading uses HuggingFace models
    Review application code or configuration that calls get_tokenizer() to see if it loads tokenizers from HuggingFace Hub or other remote repositories
    Affected if The application loads tokenizers from remote model repositories using this function
  5. Verify transformers version
    Run 'pip show transformers' to check if HuggingFace transformers v5 is installed, which triggers the TokenizersBackend fallback behavior
    Affected if Transformers version 5.x is installed and the fallback code path is reachable

A user is affected if SGLang is installed with the vulnerable get_tokenizer() function that overrides trust_remote_code=False to True, and the system loads tokenizers from remote HuggingFace model repositories.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

From vendor data
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Modify get_tokenizer() to respect the caller's trust_remote_code=False setting instead of overriding it; do not silently re-invoke with trust_remote_code=True. Alternatively, log a warning and refuse to load the tokenizer rather than bypass the security setting.

Have this fixed Scoped from the published advisory
  • Consultation2.0 h
  • Implementation3.0 h
  • Testing3.0 h
  • Review / QA2.0 h
10.0 hours of engineering $1,750
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $2,800.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-7669 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-7669 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data