Arbitrary code execution via unsandboxed Jinja2 templates
Published Aug 22, 2023 · Updated Oct 15, 2024
Code injection in LangChain before 0.0.312 allows remote attackers to execute arbitrary code by supplying a crafted prompt file. The load_prompt path accepts JSON or YAML selecting the jinja2 template format, then renders the embedded template with unsandboxed Jinja2, allowing object traversal through subclasses to reach process execution. An application must load and format an attacker-controlled prompt file; successful exploitation runs commands with the application's privileges.
Summary
What happened
Code injection in LangChain before 0.0.312 allows remote attackers to execute arbitrary code by supplying a crafted prompt file. The load_prompt path accepts JSON or YAML selecting the jinja2 template format, then renders the embedded template with unsandboxed Jinja2, allowing object traversal through subclasses to reach process execution. An application must load and format an attacker-controlled prompt file; successful exploitation runs commands with the application's privileges.
The record
- CVE
- CVE-2023-36281
- Published
- Aug 22, 2023
- Updated
- Oct 15, 2024
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 22, 2023CVE publishedPublication date reported by the CVE source.
- Oct 15, 2024Record 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?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
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
- Jinja2 prompt-file injection proof of conceptproof 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