Security Digest · Vulnerability record
CVE-2024-46946: LangChain Experimental Eval Injection vulnerability
langchainexperimental (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.
CVSS 9.3 Critical EPSS 1.4% · p72
Should you act?
Critical and remotely reachable
No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 1.4%, percentile 72: FIRST’s model estimates a 1.4% chance of exploitation activity in the next 30 days, higher than 72% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes
langchain-experimental(PyPI) >= 0.1.17, <= 0.3.0, no fixed version listed. Check your lockfile, including transitive dependencies.
What it is
langchainexperimental (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).
From the GitHub advisory
langchainexperimental (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).
Weakness type: CWE-20, CWE-95.
Product: langchain-experimental (PyPI) · Assigned by: mitre · Published: 2024-09-19
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | langchain-experimental | >= 0.1.17, <= 0.3.0 | none listed |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| n/a | n/a | see vendor advisory |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| CISA-ADP | 3.1 | 9.8 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 4.0 | 9.3 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Attack requirements: none
- Privileges required: none (no login)
- User interaction: none
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 1.39% probability of exploitation activity in the next 30 days; percentile 72.
Timeline
- — CVE record last updated
- — CVE record published by mitre
- — GitHub-reviewed advisory GHSA-p2qj-r53j-h3xj published (critical)
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-p2qj-r53j-h3xj github.com
- CVE.org record CVE-2024-46946 cve.org
- NVD entry CVE-2024-46946 nvd.nist.gov
Other references from the CVE record and advisory
- cwe.mitre.org cwe.mitre.org
- github.com github.com
- docs.sympy.org docs.sympy.org
- gist.github.com gist.github.com