CVE-2024-46946: langchain-experimental · Improper Input Validation
Affects langchain-experimentalSource CVE Database V5
Not known to be exploited · CVSS 9.8 Critical.
Data as of 26 Oct 2026, 12:29 UTC
- EPSS
- 1.3% chance of exploitation in 30 days – higher than 72% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HExploitation evidence
Disclosed: evidence found.
CVE published 19 Sep 2024
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
PyPIlangchain-experimentalpkg:pypi/langchain-experimentalOther threats | Affected
| Fixed in– |
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
- Immediately audit all deployments of LangChain Experimental to identify usage of versions 0.1.17 through 0.3.0, especially where LLMSymbolicMathChain is enabled.
- Disable or isolate the LLMSymbolicMathChain component until a secure patch or update is released.
- Avoid processing untrusted or user-supplied input through sympy.sympify or any feature that uses eval internally.
- Implement strict input validation and sanitization layers before passing data to symbolic math processing functions.
- Monitor network and system logs for unusual activity indicative of exploitation attempts, such as unexpected command executions or anomalous process behavior.
- Employ runtime application self-protection (RASP) or endpoint detection and response (EDR) tools to detect and block suspicious code execution.
- Stay updated with LangChain project announcements for patches or security advisories and apply updates promptly once available.
- Consider containerizing or sandboxing LangChain components to limit the blast radius of potential exploitation.
- Educate developers and security teams about the risks of using eval and similar functions in code processing user input.
Description
langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05).