Lucene search
K

6 matches found

OSV
OSV
added 2024/05/16 9:33 a.m.24 views

GHSA-PW38-XV9X-H8CH RunGptLLM class in LlamaIndex has a command injection

A command injection vulnerability exists in the RunGptLLM class of the llamaindex 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...

8.8CVSS9AI score0.01615EPSS
Exploits1References4
Github Security Blog
Github Security Blog
added 2024/05/16 9:33 a.m.66 views

RunGptLLM class in LlamaIndex has a command injection

A command injection vulnerability exists in the RunGptLLM class of the llamaindex 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...

8.8CVSS8AI score0.01615EPSS
Exploits1References4Affected Software2
NVD
NVD
added 2024/05/16 9:15 a.m.20 views

CVE-2024-4181

A command injection vulnerability exists in the RunGptLLM class of the llamaindex 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...

8.8CVSS9.1AI score0.01615EPSS
Exploits1References2
Vulnrichment
Vulnrichment
added 2024/05/16 9:3 a.m.22 views

CVE-2024-4181 Command Injection in run-llama/llama_index

A command injection vulnerability exists in the RunGptLLM class of the llamaindex 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...

8.8CVSS8AI score0.01615EPSS
Exploits1References2
CVE
CVE
added 2024/05/16 9:3 a.m.74 views

CVE-2024-4181

The CVE-2024-4181 issue affects llama_index (RunGptLLM class) version 0.9.47 used by RunGpt framework to connect to LLMs. Root cause: unsafe use of eval enabling a malicious or compromised LLM hosting provider to run arbitrary commands on a client machine. Impact statements in sources indicate th...

8.8CVSS7.9AI score0.01615EPSS
Exploits1References2Affected Software1
Cvelist
Cvelist
added 2024/05/16 9:3 a.m.30 views

CVE-2024-4181 Command Injection in run-llama/llama_index

A command injection vulnerability exists in the RunGptLLM class of the llamaindex 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...

8.8CVSS9.2AI score0.01615EPSS
Exploits1References2
Rows per page
Query Builder