Skip to content
Fencer Vulns
medium 5.6

CVE-2026-7669 json

sgl-project SGLang HuggingFace Transformer hf_transformers_utils.py get_tokenizer code injection

published 2026-05-02 6 mo ago modified 2026-10-26 13 d ago also GHSA-6m5f-673f-5vh7 , PYSEC-2026-3062 , EUVD-2026-26802

cvss
5.6
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 30%
public exploits
0
none known

Summary

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.

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
6 mo ago

Exploit prediction

0.37% chance of exploitation in the next 30 days, higher than 30% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • vuldb.com https://vuldb.com/vuln/360817 referenced PoC, tagged "exploit" by a source, unverified
  • github.com https://github.com/gouldnicholas/CVE-2026-7669-PoC referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 4.0 6.3 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
CNA 3.1 5.6 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R
CNA 3.0 5.6 CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R
CNA 2.0 5.1 AV:N/AC:H/Au:N/C:P/I:P/A:P/E:POC/RL:ND/RC:UR
CNA 4.0 6.3 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/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CNA 3.1 5.6 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L
CNA 2.0 5.1 AV:N/AC:H/Au:N/C:P/I:P/A:P
GitHub 3.1 5.6 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L
OSV 3.1 5.6 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L

Affected packages

ecosystem package affected fixed in
pypi sglang
<=0.5.9
 no fix listed

Affected products

  • sgl-project SGLang

Classification

Weakness
  • CWE-94 Improper Control of Generation of Code
  • CWE-74 Improper Neutralization of Special Elements in Output Used by a Downstream Component
  • CWE-20 Improper Input Validation

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.