Arbitrary code execution via implicit Python REPL
Published Jun 16, 2024 · Updated Aug 2, 2024
Arbitrary code execution in LangChain Experimental before 0.0.61 allows attackers to run Python via REPL-backed agents. The dataframe-agent factories and PALChain enabled Python REPL-backed paths without requiring the allow_dangerous_code opt-in. Applications must pass attacker-influenced input into an affected agent or chain; resulting code runs with the host Python process privileges.
Summary
What happened
Arbitrary code execution in LangChain Experimental before 0.0.61 allows attackers to run Python via REPL-backed agents. The dataframe-agent factories and PALChain enabled Python REPL-backed paths without requiring the allow_dangerous_code opt-in. Applications must pass attacker-influenced input into an affected agent or chain; resulting code runs with the host Python process privileges.
The record
- CVE
- CVE-2024-38459
- Published
- Jun 16, 2024
- Updated
- Aug 2, 2024
- Vendor
- LangChain
- Product
- LangChain Experimental
- Classifications
- CWE-276, T1059.006
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 16, 2024CVE publishedPublication date reported by the CVE source.
- Aug 2, 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?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <0.0.61
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.
Public exploit references
No public exploit references are available in this record.
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