LangChain vulnerable to code injection
CVE-2023-29374 · GHSA-fprp-p869-w6q2 · published 2023-04-05 · updated 2024-09-30
- Severity
- Critical
- CVSS score
- 9.8
- Chance of exploitation (EPSS)
- 39.7%
- Fixed in
- No fix yet
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Total
- CISA SSVC
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec() method.
No fixed release is listed yet for langchain. Follow the source advisory for updates, and until one ships:
General guidance from ShieldPi, not a vendor fix
- Command or code injection. Remove or disable the affected server or tool, or run it in a sandbox with no secrets in its environment.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| langchain | PyPI | <= 0.0.131 | No fix yet |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- CriticalLangchain SQL Injection vulnerabilitylangchain
- CriticalLangchain vulnerable to arbitrary code execution via the evaluate function in the numexpr librarylangchain
- Criticallangchain vulnerable to arbitrary code executionlangchain
- CriticalLangChain vulnerable to arbitrary code executionlangchain
- CriticalLangChain vulnerable to arbitrary code executionlangchain
- CriticalLangChain vulnerable to arbitrary code executionlangchain
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.