When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agents

Matous Kozak, Roshanak Zilouchian Moghaddam, Kalpathy Sivaraman

Keywords: Large Language Models, Autonomous Software Agents, Software Vulnerabilities, Cybersecurity Risks, Vulnerability Mitigation

TL;DR: LLM-based coding agents can speed up development but often introduce security vulnerabilities, with 21% of trajectories found to be unsafe - though GPT-4.1 showed strong mitigation capabilities.

Abstract:

LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood. These agents, while capable of accelerating software development, may exhibit unsafe behaviors during normal operation that manifest as cybersecurity vulnerabilities. We conducted the first systematic safety evaluation of autonomous coding agents, analyzing over 12,000 actions across five state-of-the-art models (GPT-4o, GPT-4.1, Claude variants) on 93 real-world software setup tasks.
Our findings reveal significant security concerns: 21% of agent trajectories contained insecure actions, with models showing substantial variation in unsafe behavior. We developed a high-precision detection system that identified four major vulnerability categories, with information exposure (CWE-200) being the most prevalent one.
We also evaluated mitigation strategies including feedback mechanisms and security reminders with various effectiveness between models. GPT-4.1 demonstrated exceptional security awareness with 96.8% mitigation success.

Archival Option: The authors of this submission want it to appear in the archival proceedings.

Submission Number: 28