Llama Stack log information leakage vulnerability

Llama Stack is a core building block for simplified artificial intelligence application development, open-sourced by Meta Llama. Versions of Llama Stack prior to 0.4.0rc3 contained a vulnerability related to log information leakage. This vulnerability stemmed from the fact that the log...

Security Bulletin: Multiple Vulnerabilities affecting IBM Watson Studio in Cloud Pak for Data are addressed

Summary There are multiple vulnerabilities impacting IBM Watson Studio in Cloud Pak for Data. This bulletin identifies the steps to take to address the vulnerabilities. Vulnerability Details CVEID:CVE-2025-7647 DESCRIPTION: The llama-index-core package, up to version 0.12.44, contains a...

Rethinking On-Device LLM Reasoning: Why Analogical Mapping Outperforms Abstract Thinking for IoT DDoS Detection

The rapid expansion of IoT deployments has intensified cybersecurity threats, notably Distributed Denial of Service DDoS attacks, characterized by increasingly sophisticated patterns. Leveraging Generative AI through On-Device Large Language Models ODLLMs provides a viable solution for real-time...

LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation

In this study, we propose a homotopy-inspired prompt obfuscation framework to enhance understanding of security and safety vulnerabilities in Large Language Models LLMs. By systematically applying carefully engineered prompts, we demonstrate how latent model behaviors can be influenced in...

Many Hands Make Light Work: An LLM-Based Multi-Agent System for Detecting Malicious PyPI Packages

Malicious code in open-source repositories such as PyPI poses a growing threat to software supply chains. Traditional rule-based tools often overlook the semantic patterns in source code that are crucial for identifying adversarial components. Large language models LLMs show promise for software...

Exploit for CVE-2024-50050

--- 💀 LlamaStack-RCE: CVE-2024-50050 Supply Chain Exploitatio...

Linux Distros Unpatched Vulnerability : CVE-2026-21869

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the ndiscard parameter is parsed directly from JSON input in the...

CVE-2024-14021

LlamaIndex run-llama/llamaindex versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.loadfromdisk in llamaindex/indices/managed/bgem3/base.py. The function uses pickle.load to deserialize multiembedstore.pkl from a user-supplied persistdir without...

Deserialization of Untrusted Data

Overview llama-index is an Interface between LLMs and your data Affected versions of this package are vulnerable to Deserialization of Untrusted Data via the loadfromdisk function. An attacker can execute arbitrary code by supplying a crafted multiembedstore.pkl file in a user-controlled director...

3m (>=0.1.0, <=0.1.3), aap-llamaindex (>=0.1.1.dev1, <=0.2.0) +354 more potentially affected by CVE-2024-14021 via llama-index (>=0.4.17, <=0.14.23)

llama-index PYPI version =0.4.17, =0.1.0, =0.1.1.dev1, =0.1.8, =0.0.2, =1.1.0a20250502, =0.10.0, =1.4.3, =0.1.0a0.dev0, =0.2.0a0, =0.1.0, =0.1.0a1, =1.0.1 and more Source cves: CVE-2024-14021 Source advisory: SNYK:PYTHON-LLAMAINDEX-14917171...

Deserialization of Untrusted Data

Overview llama-index-indices-managed-bge-m3 is a LlamaIndex Indices Integration: Bge-M3 Affected versions of this package are vulnerable to Deserialization of Untrusted Data via the loadfromdisk function. An attacker can execute arbitrary code by supplying a crafted multiembedstore.pkl file in a...

3m (>=0.1.0, <=0.1.3), aap-llamaindex (>=0.1.1.dev1, <=0.2.0) +354 more potentially affected by CVE-2024-58339 via llama-index (>=0.4.17, <=0.14.23)

llama-index PYPI version =0.4.17, =0.1.0, =0.1.1.dev1, =0.1.8, =0.0.2, =1.1.0a20250502, =0.10.0, =1.4.3, =0.1.0a0.dev0, =0.2.0a0, =0.1.0, =0.1.0a1, =1.0.1 and more Source cves: CVE-2024-58339 Source advisory: SNYK:PYTHON-LLAMAINDEX-14917160...

Use of NullPointerException Catch to Detect NULL Pointer Dereference

Overview Affected versions of this package are vulnerable to Use of NullPointerException Catch to Detect NULL Pointer Dereference in the MultimodalTokenize function that improperly processes NULL from mtmdhelperbitmapinitfrombuf function of vendored llama.cpp. An attacker can cause the applicatio...

CVE-2024-58339

LlamaIndex run-llama/llamaindex versions up to and including 0.12.2 contain an uncontrolled resource consumption vulnerability in the VannaPack VannaQueryEngine implementation. The customquery logic generates SQL statements from a user-supplied prompt and executes them via vn.runsql without...

PYSEC-2026-85

LlamaIndex run-llama/llamaindex versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.loadfromdisk in llamaindex/indices/managed/bgem3/base.py. The function uses pickle.load to deserialize multiembedstore.pkl from a user-supplied persistdir without...

SUSE CVE-2026-21869

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the ndiscard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fill...

CVE-2026-21869

A flaw was found in llama.cpp. A remote attacker can exploit an input validation vulnerability in the server's completion endpoints. By supplying a negative value for the ndiscard parameter in JSON input, an attacker can cause out-of-bounds memory writes. This can lead to a process crash or enabl...

UBUNTU-CVE-2026-21869

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the ndiscard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fill...

CVE-2026-21869

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the ndiscard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fill...

CVE-2026-21869

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the ndiscard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fill...