Denial of service via backtracking action regex
Published Jan 12, 2026 · Updated Jan 12, 2026
Regular expression denial of service in LangChain 0.3.1 and earlier allows attackers to cause parsing delays via crafted model output. MRKLOutputParser.parse() applies a backtracking-prone action-extraction regex to untrusted text, causing excessive CPU use on crafted nonmatching input. Reachability requires an application to pass attacker-influenced LLM output into this parser; exploitation delays or stalls parsing without reported data access or modification.
Summary
What happened
Regular expression denial of service in LangChain 0.3.1 and earlier allows attackers to cause parsing delays via crafted model output. MRKLOutputParser.parse() applies a backtracking-prone action-extraction regex to untrusted text, causing excessive CPU use on crafted nonmatching input. Reachability requires an application to pass attacker-influenced LLM output into this parser; exploitation delays or stalls parsing without reported data access or modification.
The record
- CVE
- CVE-2024-58340
- Published
- Jan 12, 2026
- Updated
- Jan 12, 2026
- Vendor
- LangChain
- Product
- LangChain
- Classifications
- CWE-1333, CAPEC-492, T1499.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jan 12, 2026CVE publishedPublication date reported by the CVE source.
- Jan 12, 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 <=0.3.1
What conditions does exploitation require?
What is affected?
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
- huntr MRKLOutputParser ReDoS proof of conceptproof of concept · unverified
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