CVE-2025-6211Medium· 6.5▾ SunlitLlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class
▾ Sunlit zone — Low / medium · no exploitation signal
impact 35.8 · likelihood 0.1 · 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
0.3%
0.3% → 0.3%
Last analysed / modified upstream
A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to but excluding version 0.12.41, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.
llama-index < 0.12.41llama-index-readers-docugami < 0.3.1Upgrade to a patched release:
llama-index 0.12.41llama-index-readers-docugami 0.3.1Connected 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-2024-4181High· 8.8RunGptLLM class in LlamaIndex has a command injection
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-2025-1750Critical· 9.8An SQL injection vulnerability exists in the delete function of DuckDBVectorStore in run-llama/llama_index version v0.12.19. This vulnera…