Intel / article

Evaluating and Preventing Security Smells in AI-Generated Ansible Code

Source: Pandu Ranga Reddy Konala, Vimal Kumar, David Bainbridge, Junaid Haseeb
Author: Pandu Ranga Reddy Konala, Vimal Kumar, David Bainbridge, Junaid Haseeb
Date: Published Aug 27, 2026

Why it matters

Ungated AI-generated Ansible ships CIS-noncompliant infrastructure from every model tested; folding CIS benchmarks and Ansible practice into the prompt gets the best model to 95-100% compliance, prevention at synthesis rather than detection after deploy.

Read the source ↗arxiv.org

Recommended reads

articleGrounding AI Agents in Contracts: An Empirical Evaluation of Spec-Driven Test GenerationMichele Tufano, James McClure, Jos\'e Cambronero, Runxiang Cheng, Sherry Y. Shi, Renyao Wei, Dorothy Chen, Franjo Ivan\v{c}i\'c, Livio Dalloro, Pat Rondon
articleAgentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration TestingIsrat Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md. Jakir Hossain, M. F. Mridha
articleA Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-Agent AdoptionYegor Denisov-Blanch, Shyam Agarwal, Pavel Azaletskiy, Hao He, Rylan Schaeffer, Brando Miranda, Bogdan Vasilescu, Sanmi Koyejo