Remote code execution via unsandboxed Jinja templates
Published Apr 20, 2026 · Updated Apr 20, 2026
Server-side template injection in SGLang before 0.5.11 allows remote attackers to execute Python code through the /v1/rerank endpoint. The _get_jinja_env() function in serving_rerank.py renders a model-supplied tokenizer.chat_template with unsandboxed jinja2.Environment(), permitting unsafe attribute traversal into command-execution primitives. Exploitation requires an operator to load an attacker-crafted GGUF reranker model and a request to reach the endpoint; code runs with the SGLang service's privileges.
Summary
What happened
Server-side template injection in SGLang before 0.5.11 allows remote attackers to execute Python code through the /v1/rerank endpoint. The _get_jinja_env() function in serving_rerank.py renders a model-supplied tokenizer.chat_template with unsandboxed jinja2.Environment(), permitting unsafe attribute traversal into command-execution primitives. Exploitation requires an operator to load an attacker-crafted GGUF reranker model and a request to reach the endpoint; code runs with the SGLang service's privileges.
The record
- CVE
- CVE-2026-5760
- Published
- Apr 20, 2026
- Updated
- Apr 20, 2026
- Vendor
- SGLang
- Product
- SGLang
- Classifications
- CWE-94, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Apr 20, 2026CVE publishedPublication date reported by the CVE source.
- Apr 20, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.59
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- SGLang SSTI to RCE PoCproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo