# Inducing Vulnerable Code Generation in LLM Coding Assistants

arXiv: https://arxiv.org/abs/2504.15867 · HTML: https://mlsanity.com/paper/2504.15867/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2025.

## Built on by (most cited first, 5 of 5)

- [Population-Aligned Persona Generation for LLM-based Social Simulation](https://mlsanity.com/paper/2509.10127/) (2025)
- [CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs](https://mlsanity.com/paper/2506.11059/) (2025)
- [Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs](https://mlsanity.com/paper/2509.02372/) (2025)
- [SoK: Understanding (New) Security Issues Across AI4Code Use Cases](https://mlsanity.com/paper/2512.18456/) (2025)
- [Security in LLM-Assisted Coding: A Systematic Literature Review](https://mlsanity.com/paper/2610.15482/) (2026)

## Abstract (arXiv)

Due to insufficient domain knowledge, LLM coding assistants often reference related solutions from the Internet to address programming problems. However, incorporating external information into LLMs' code generation process introduces new security risks. In this paper, we reveal a real-world threat, named HACKODE, where attackers exploit referenced external information to embed attack sequences, causing LLMs to produce code with vulnerabilities such as buffer overflows and incomplete validations. We designed a prototype of the attack, which generates effective attack sequences for potential diverse inputs with various user queries and prompt templates. Through the evaluation on two general LLMs and two code LLMs, we demonstrate that the attack is effective, achieving an 84.29% success rate. Additionally, on a real-world application, HACKODE achieves 75.92% ASR, demonstrating its real-world impact.