CVE-2024-4181High· 8.8▾ TwilightRunGptLLM class in LlamaIndex has a command injection
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 48.4 · likelihood 0.4 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Jul 8.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via OSV
Last analysed / modified upstream
2.1%
2.1% → 2.1%
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.
llama-index < 0.10.13llama-index-llms-rungpt < 0.1.3Upgrade to a patched release:
llama-index 0.10.13llama-index-llms-rungpt 0.1.3Connected by shared product, vendor, weakness, or advisory.
CVE-2025-1793Critical· 9.8llama_index vulnerable to SQL Injection
CVE-2025-7707High· 7.1llama-index has Insecure Temporary File
CVE-2024-12911High· 7.1LlamaIndex vulnerable to Creation of Temporary File in Directory with Insecure Permissions
CVE-2025-1752High· 7.5LlamaIndex Vulnerable to Denial of Service (DoS)
CVE-2025-6211Medium· 6.5LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class
CVE-2025-1750Critical· 9.8An SQL injection vulnerability exists in the delete function of DuckDBVectorStore in run-llama/llama_index version v0.12.19. This vulnera…