CVE Intelligence
Medium Injection exploit reference

CVE-2026-7669 — sgl-project SGLang HuggingFace Transformer hf_transformers_utils.py get_tokenizer code injection

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.

Published May 2, 2026 · Updated Oct 13, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: VulDB

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • EPSS 0.4% (30-day exploitation probability)+5
  • Technical severity (medium)+3
  • CISA SSVC: exploitation "poc"+5

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
0.42%
ahead of 35% of scored CVEs · Oct 14, 2026
Affects
Sgl-project
SGLang
CVSS base
5.6
Medium · 2 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation
Proof of concept
none · proof-of-concept · active
Automatable
No
can an attacker script the kill-chain steps
Technical impact
Partial
partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (Sgl-project SGLang).
  2. The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
  3. No fix documented in the sources: reduce exposure and monitor the vendor advisory.
  4. Search available logs for exploit probes matching the vulnerability class (injection), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
Sgl-project SGLang version 0.5.0version 0.5.1version 0.5.2version 0.5.3version 0.5.4version 0.5.5version 0.5.6version 0.5.7
and 2 more version 0.5.8version 0.5.9
Vulnerable CVE Program (cve.org) e CISA ADP

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector
Network
Attack complexity
High
Privileges required
None
User interaction
None
Scope
Unchanged
Confidentiality
Low
Integrity
Low
Availability
Low

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactScored by
6.3 CVSS 4.0 Medium — — cna@vuldb.com via NIST National Vulnerability Database
6.3 CVSS 4.0 Medium — — VulDB via CVE Program (cve.org) e CISA ADP
5.6 CVSS 3.1 Medium 2.2 3.4 cna@vuldb.com via NIST National Vulnerability Database
5.6 CVSS 3.1 Medium — — VulDB via CVE Program (cve.org) e CISA ADP
5.6 CVSS 3.0 Medium — — VulDB via CVE Program (cve.org) e CISA ADP
5.1 CVSS 2.0 Medium 4.9 6.4 cna@vuldb.com via NIST National Vulnerability Database
5.1 CVSS 2.0 Medium — — VulDB via CVE Program (cve.org) e CISA ADP
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L (score shown at the top: cna@vuldb.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-74 · Injection

Other CVEs with this weakness →

EPSS over time FIRST

Oct 13, 2026 → Oct 14, 2026 · 2 reading(s) · max 0.42%

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
  • Look for parameters with command/query metacharacters and unexpected child processes of the service.
web/proxy/WAF logsnetwork IDS/IPSapplication logsendpoint telemetry (EDR)

Timeline

What happened to this CVE, newest first.

  • 2026
  • Affected products added · sgl-project/sglang
    Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 13, 2026
  • CVSS changed · 5.6
    Oct 13, 2026 · NIST National Vulnerability Database
  • Source status changed · → Deferred
    Oct 13, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 13, 2026 · NIST National Vulnerability Database
  • CVE published
    May 2, 2026 · VulDB

Source activity

Repeated readings are counted rather than listed.

  • 1× Official description updated · Oct 13, 2026 – Oct 13, 2026

References

4 on the record

Elsewhere on this site

Sgl-project
every CVE for this vendor
Injection
same class
CWE-74
other pages naming this weakness

Related CVEs (same products)

  • CVE-2026-110809 sgl-project SGLang Session Cleanup session_controller.py Session.create_req denial of service 19h
  • CVE-2026-110807 sgl-project SGLang generate Endpoint io_struct.py denial of service 20h
  • CVE-2026-109229 SGLang through 0.5.21 Decompression Bomb DoS via NanoNemotronVLImageProcessor 3d
  • CVE-2026-109228 SGLang through 0.5.21 Resource Budget Bypass via GLM-V Video Parameters 3d
  • CVE-2026-109225 SGLang through 0.5.21 Memory Exhaustion DoS via /v1/audio/transcriptions Upload 3d
  • CVE-2026-109226 SGLang through 0.5.21 Audio Decompression Amplification via load_audio 3d

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No fixed version, patch or mitigation documented.
  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-7669 is "sgl-project SGLang HuggingFace Transformer hf_transformers_utils.py get_tokenizer code injection", rated Medium. It affects SGLang (Sgl-project); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 5.6 describes technical severity. EPSS 0.42% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.