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-2026-41134 Kiota: Code Generation Literal Injection

Kiota is an OpenAPI based HTTP Client code generator. Versions prior to 1.31.1 are affected by a code-generation literal injection vulnerability in multiple writer sinks for example: serialization/deserialization keys, path/query parameter mappings, URL template metadata, enum/property metadata,...

SQLi

SQL Injection: An Elite Bug Bounty Hunter's Field Manual SQL...

Broken by Default: A Formal Verification Study of Security Vulnerabilities in AI-Generated Code

AI coding assistants are now used to generate production code in security-sensitive domains, yet the exploitability of their outputs remains unquantified. We address this gap with Broken by Default: a formal verification study of 3,500 code artifacts generated by seven frontier LLMs across 500...

Arbitrary Code Injection

Langflow is vulnerable to Arbitrary Code Injection. The vulnerability is due to the validation process dynamically executing LLM‑generated Python code via exec, where the validation routine runs the generated code and an attacker who can influence the model output can achieve arbitrary server‑sid...

PT-2026-27948

Name of the Vulnerable Software and Affected Versions Widget Wrangler versions prior to 2.3.9 Description A code injection issue exists in Jonathan Daggerhart Widget Wrangler. The issue involves improper control of code generation. This allows for code injection. Recommendations Update Widget...

Code Injection

org.apache.avro, avro-compiler is vulnerable to Code Injection. The vulnerability is due to improper validation of untrusted Avro schemas during specific record generation, where attacker-controlled schema content can be incorporated into generated Java source code without sufficient sanitization...

AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software

Large language models LLMs for code generation are becoming integral to modern software development, but their real-world prevalence and security impact remain poorly understood. We present the first large-scale empirical study of AI-generated code AIGCode in the wild. We build a high-precision...

Security Vulnerabilities in AI-Generated Code: A Large-Scale Analysis of Public GitHub Repositories

This paper presents a comprehensive empirical analysis of security vulnerabilities in AI-generated code across public GitHub repositories. We collected and analyzed 7,703 files explicitly attributed to four major AI tools: ChatGPT 91.52%, GitHub Copilot 7.50%, Amazon CodeWhisperer 0.52%, and...

EUVD-2021-0532

Malware in sbrugna...

Vibe Coding Is the New Open Source—in the Worst Way Possible

As developers increasingly lean on AI-generated code to build out their software—as they have with open source in the past—they risk introducing critical security failures along the way...

Investigating Security Implications of Automatically Generated Code on the Software Supply Chain

In recent years, various software supply chain SSC attacks have posed significant risks to the global community. Severe consequences may arise if developers integrate insecure code snippets that are vulnerable to SSC attacks into their products. Particularly, code generation techniques, such as...

EvilAI Operators Use AI-Generated Code and Fake Apps for Far-Reaching Attacks

Combining AI-generated code and social engineering, EvilAI operators are executing a rapidly expanding campaign, disguising their malware as legitimate applications to bypass security, steal credentials, and persistently compromise organizations worldwide...

Secure Vibe Coding: The Complete New Guide

DALL-E for coders? That's the promise behind vibe coding, a term describing the use of natural language to create software. While this ushers in a new era of AI-generated code, it introduces "silent killer" vulnerabilities: exploitable flaws that evade traditional security tools despite perfect...

CVE-2024-56051

Improper Control of Generation of Code 'Code Injection' vulnerability in VibeThemes WPLMS allows Code Injection.This issue affects WPLMS: from n/a before 1.9.9.5...

DEBIAN-CVE-2024-7883

When using Arm Cortex-M Security Extensions CMSE, Secure stack contents can be leaked to Non-secure state via floating-point registers when a Secure to Non-secure function call is made that returns a floating-point value and when this is the first use of floating-point since entering Secure state...

PT-2024-38657

Name of the Vulnerable Software and Affected Versions Arm Cortex-M Security Extensions CMSE affected versions not specified Description The issue allows Secure stack contents to be leaked to Non-secure state via floating-point registers when a Secure to Non-secure function call is made that retur...

GHSA-RRQQ-FV6M-692M 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-2024-5826

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-2024-5826 Remote Code Execution via Prompt Injection in vanna-ai/vanna

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...