CVE-2024-3098Critical· 9.8▾ Midnightllama-index-core Prompt Injection vulnerability leading to Arbitrary Code Execution
▾ Midnight zone — Critical, or high with PoC / in-the-wild
impact 53.9 · likelihood 0.2 · 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 Oct 27.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via OSV
Last analysed / modified upstream
1.0%
A vulnerability was identified in the exec_utils class of the llama_index package, specifically within the safe_eval function, allowing for prompt injection leading to arbitrary code execution. This issue arises due to insufficient validation of input, which can be exploited to bypass method restrictions and execute unauthorized code. The vulnerability is a bypass of the previously addressed CVE-2023-39662, demonstrated through a proof of concept that creates a file on the system by exploiting the flaw.
llama-index-core < 0.10.24Upgrade to a patched release:
llama-index-core 0.10.24Connected by shared product, vendor, weakness, or advisory.
CVE-2025-3108Medium· 5.0LlamaIndex has Incomplete Documentation of Program Execution related to JsonPickleSerializer component
CVE-2025-7647High· 7.3The llama-index-core package, up to version 0.12.44, contains a vulnerability in the `get_cache_dir()` function where a predictable, hardcoded directory path `/tmp/llama_index` is used on Linux systems without proper security controls
CVE-2025-5302High· 8.6LlamaIndex affected by a Denial of Service (DOS) in JSONReader
CVE-2025-6208Medium· 5.3llama-index-core vulnerable to Uncontrolled Resource Consumption
CVE-2025-5472Medium· 6.5LlamaIndex vulnerable to DoS attack through uncontrolled recursive JSON parsing
CVE-2025-6209High· 7.5LlamaIndex vulnerable to Path Traversal attack through its encode_image function