RunGptLLM class in LlamaIndex has a command injection
CVE-2024-4181 · GHSA-pw38-xv9x-h8ch · published 2024-05-16 · updated 2024-05-24
- Severity
- High
- CVSS score
- 8.8
- Chance of exploitation (EPSS)
- 2.1%
- Fixed in
- 0.10.13
- Exploitation No known exploitation
- Automatable No
- Technical impact Total
- CISA SSVC
A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs). The vulnerability arises from the improper use of the eval function, allowing a malicious or compromised LLM hosting provider to execute arbitrary commands on the client's machine. This issue was fixed in version 0.10.13. The exploitation of this vulnerability could lead to a hosting provider gaining full control over client machines.
Upgrade llama-index to 0.10.13 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| llama-index | PyPI | < 0.10.13 | 0.10.13 |
- 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
- Criticalllama_index vulnerable to SQL Injectionllama-index
- CriticalSQL injection in llama-indexllama-index
- Criticalllama-index vulnerable to arbitrary code executionllama-index
- Highllama-index has Insecure Temporary Filellama-index
- HighLlamaIndex Vulnerable to Denial of Service (DoS)llama-index
- HighLlamaIndex vulnerable to Creation of Temporary File in Directory with Insecure Permissionsllama-index
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.