Security readout for executives and security teams
Plain-English summary
A crafted LLM response can make LangChain's MRKLOutputParser consume excessive CPU while parsing tool actions. Apps using vulnerable LangChain and feeding attacker-influenced model output into this parser can suffer delays or denial of service. The source bundle does not show confirmed real-world exploitation.
Executive priority
Prioritize review for customer-facing AI agents, chatbots, or automation services using LangChain MRKL parsing. This is a denial-of-service risk, not a data theft claim in the provided evidence, but high availability impact makes timely remediation appropriate.
Technical view
LangChain through 0.3.1 has CWE-1333 ReDoS in MRKLOutputParser.parse() at libs/langchain/langchain/agents/mrkl/output_parser.py. The vulnerable regex is backtracking-prone when extracting tool actions from model output, allowing attacker-influenced parsed text to trigger high CPU consumption and parsing delays.
Likely exposure
Exposure is likely limited to applications running LangChain up to and including 0.3.1 that use MRKLOutputParser.parse() on untrusted or prompt-injectable LLM output. General LangChain use without this parser path is not proven exposed by the bundle.
Exploitation context
The bundle references public technical reporting and exploit material, but KEV is false and no cited source states active exploitation. Practical abuse requires a path to influence text parsed by MRKLOutputParser, such as prompt injection in an agent workflow.
Researcher notes
The key uncertainty is patch specificity: the bundle states LangChain through 0.3.1 is affected but does not name a fixed version. Avoid assuming all LangChain deployments are vulnerable; validate the parser path and whether prompt injection or untrusted output can reach it.
Mitigation direction
- Identify LangChain versions and MRKLOutputParser usage in deployed services.
- Check LangChain and advisory guidance for the fixed or non-affected release.
- Upgrade vulnerable LangChain deployments when a vendor-supported fixed version is confirmed.
- Apply parser timeouts, request limits, and worker isolation around LLM output parsing.
- Reduce direct parsing of attacker-influenced model output where feasible.
Validation and detection
- Search dependency manifests and lockfiles for LangChain versions up to 0.3.1.
- Review agent code for MRKLOutputParser.parse() or MRKL agent output parsing.
- Trace whether external users can influence model output reaching the parser.
- Confirm runtime controls cap CPU time, request duration, and queue impact.
- Retest after upgrade or mitigation using non-destructive malformed-output cases.
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-1333: Exact CWE lookup
Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupCVE-2024-58340 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- High
- CVSS
- 8.7 (4.0)
- Known Exploited
- No
- Published
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
SSVC decision data
CVSS vector scores
1 official scoreWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N——VulnCheckVulnerability scoring details
Base CVSS 4.0 score
8.7HighVector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- https://huntr.com/bounties/e7ece02c-d4bb-4166-8e08-6baf4f8845bbCVE reference, VulnCheck · technical-description, exploit
- https://www.langchain.com/CVE reference, VulnCheck · product
- https://github.com/langchain-ai/langchainCVE reference, VulnCheck · product
- https://www.vulncheck.com/advisories/langchain-mrkloutputparser-redosCVE reference, VulnCheck · third-party-advisory
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Inefficient Regular Expression Complexity
Inefficient Regular Expression Complexity represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.