CVE-2023-29374

Exp

In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.

Published: 2023-04-04 Last update: 2026-06-17 Assigner: [email protected] Source: [email protected]
NVD Status：Modified，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2023-29374 is rated High Exploit Risk (93.7/100): CVSS Critical severity, with high exploitation likelihood (EPSS 39.65%, 98th percentile). 2 public exploit reference(s) are indexed (Exploit-DB). EPSS rose +35.88% over the last day, indicating growing attacker interest. Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2023-29374

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2023-29374

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-06-15 3.77% 39.65% +35.88%
2 2026-04-15 4.97% 3.77% -1.20%
3 2026-04-06 — 4.97% —

Full EPSS history (33 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2023-29374

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
9.8 3.1 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 5.9 [email protected]
9.8 3.1 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 5.9 134c704f-9b21-4f2e-91b3-4a467353bcc0

Weakness enumeration for CVE-2023-29374

GitHub Security Advisory for CVE-2023-29374

GHSA-fprp-p869-w6q2 · Severity: critical · Ecosystem: pip — LangChain vulnerable to code injection

Affected software / configurations for CVE-2023-29374

Vendor Product Version Raw CPE
langchain langchain <= 0.0.131 cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*

References for CVE-2023-29374

cvelogic Threat Intelligence