# Trust but Verify? Uncovering the Security Debt of Autonomous Coding Agents

arXiv: https://arxiv.org/abs/2607.12428 · HTML: https://mlsanity.com/paper/2607.12428/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 10 of 10)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap](https://mlsanity.com/paper/2410.06107/) (2024)
- [Agentic AI Software Engineers: Programming with Trust](https://mlsanity.com/paper/2502.13767/) (2025)
- [Good Vibrations? A Qualitative Study of Co-Creation, Communication, Flow, and Trust in Vibe Coding](https://mlsanity.com/paper/2509.12491/) (2025)
- [How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests](https://mlsanity.com/paper/2601.17581/) (2026)
- [Understanding Dominant Themes in Reviewing Agentic AI-authored Code](https://mlsanity.com/paper/2601.19287/) (2026)
- [Do Autonomous Agents Contribute Test Code? A Study of Tests in Agentic Pull Requests](https://mlsanity.com/paper/2601.03556/) (2026)
- [Artificial Intelligence in Open Source Software Engineering: A Foundation for Sustainability](https://mlsanity.com/paper/2602.07071/) (2026)
- [Testing with AI Agents: An Empirical Study of Test Generation Frequency, Quality, and Coverage](https://mlsanity.com/paper/2603.13724/) (2026)

## Abstract (arXiv)

The increasing adoption of autonomous coding agents accelerates software development but also introduces scoped security risks within high-impact file paths that can outpace traditional human review capacity. While prior research has primarily evaluated these systems in terms of functional correctness and productivity, this paper presents a large-scale empirical study using the AIDev dataset to systematically characterize security code smells in agent-generated pull requests (PRs). Through a combination of a validated LLM-as-a-judge framework and manual qualitative analysis, we identify and classify security misconfigurations across 16,112 file changes spanning 4,022 pull requests. Our results reveal that 38.9% of agent-generated PRs contain at least one security smell, with supply chain integrity issues accounting for 82.3% of all detected security smells. Furthermore, hard-coded credentials constitute 99.6% of all critical-severity security smells. Crucially, we find that human collaborators are responsible for introducing 67.6% of genuine leaked secrets within these agent-assisted workflows, while existing automated and human review processes fail to detect 81.1% of these credentials prior to integration. These findings highlight substantial security risks in agent-assisted software development workflows and suggest a potential reduction in developer vigilance. They also underscore the urgent need for context-aware security guardrails implemented directly at the point of human-AI collaboration.