Newer and Bigger, but Safer? A Longitudinal Study of the Functionality-Security Gap in LLM-Generated Code

Large Language Models LLMs are widely used to generate code. Although their functional plausibility keeps improving, the generated code often contains security vulnerabilities. The functionality-security gap captures code that passes functional tests but fails security tests. A recent longitudina...

LLMVul: A Vulnerability-Labeled Dataset of LLM-Generated C/C++ Functions from Real Production Repositories

Large language models LLMs are increasingly used to generate and assist with software development, yet existing vulnerability datasets largely focus on human-written code or controlled prompting environments. This limits the ability to study security weaknesses in LLM-generated code as it appears...

Prompt Structure Redistributes, Not Reduces: An Empirical Analysis of Security-Weaknesses in LLM-Generated Python Code

Large Language Models LLMs increasingly generate code from natural-language prompts, making prompt engineering a key mechanism for shaping the security of generated software. Structured and security-oriented prompts are widely used to encourage safer code, yet their effects extend beyond whether...

Vibe Coding and Web Application Security: A Twin-Prompt Study

Large language models increasingly generate complete web applications from natural-language prompts, raising the question of whether explicitly requesting security best practice improves the result. We study six functionally distinct web applications, each generated in two prompt variants that ar...

IBM Langflow OSS Code Execution Vulnerability (CNVD-2026-32369)

IBM Langflow OSS is the open-source version of Langflow that IBM officially integrates and promotes. IBM Langflow OSS has a code execution vulnerability. This vulnerability stems from the failure to properly handle components generated by the LLM during the Agentic Assistant validation process. T...

CVE-2026-9196

IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components. The application executes model‑generated Python code in the backend during validation prior to user...

PT-2026-68304

Name of the Vulnerable Software and Affected Versions IBM Langflow OSS versions 1.0.0 through 1.10.3 Description An authenticated attacker can execute unintended code during Agentic Assistant validation because the application improperly handles LLM-generated components. The system executes Pytho...

Arbitrary Code Injection

Overview flowise is a Flowiseai Server Affected versions of this package are vulnerable to Arbitrary Code Injection via the run method in the CSVAgents class. An attacker can execute arbitrary code in the context of the server process by sending crafted prompts to a chatflow using the CSV Agent...

PYSEC-2026-562 vanna vulnerable to remote code execution caused by prompt injection

In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the exec function in...

CVE-2026-42079

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

CVE-2026-42079 PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

CVE-2026-42079 PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

CVE-2026-42079: Improper Neutralization of Directives in Dynamically Evaluated Code

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

An Empirical Security Evaluation of LLM-Generated Cryptographic Rust Code

Developers and organizations are using Large Language Models LLMs to generate security-critical code more frequently than ever, including cryptographic solutions for their products. This study presents an empirical evaluation of cryptographic security in 240 Rust code samples for two crypto...

CVE-2026-33873

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

CVE-2026-33873: Improper Control of Generation of Code

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

Watermarking LLM-Generated Datasets in Downstream Tasks

Large Language Models LLMs have experienced rapid advancements, with applications spanning a wide range of fields, including sentiment classification, review generation, and question answering. Due to their efficiency and versatility, researchers and companies increasingly employ LLM-generated da...

CVE-2025-1497

A vulnerability, that could result in Remote Code Execution RCE, has been found in PlotAI. Lack of validation of LLM-generated output allows attacker to execute arbitrary Python code. Vendor commented out vulnerable line, further usage of the software requires uncommenting it and thus accepting t...

CVE-2025-1497: Improper Control of Generation of Code

A vulnerability, that could result in Remote Code Execution RCE, has been found in PlotAI. Lack of validation of LLM-generated output allows attacker to execute arbitrary Python code. Vendor commented out vulnerable line, further usage of the software requires uncommenting it and thus accepting t...

Malicious code in omigo-data-analytics (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 ae4cfba5955464b4ebdf67da4386ccc25b7431d6dfc11e70146b23c0a8185860 The package looks like a beginning for a further work. In fact, the uploader has shortly published a few similar packages appearing to be e.g. an integration f...