"Tab, Tab, Bug": Security Pitfalls of Next Edit Suggestions in AI-Integrated IDEs

arXiv:2602.06759 · cs.CR, cs.HC · Submitted 2026-02-06 · Read on arXiv

cs.CR, cs.HC

Submitted: 2026-02-06

Updated: 2026-09-09

Comments: To appear in ACM CCS 2026

DOI: 10.1145/3830454.3846699

Code: https://github.com/tree-sitter/tree-sitter

Project page: https://microsoft.github.io/languageserver-protocol

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 16× in this paper · explained in 2 episodes
• Next Edit Suggestions — 15× in this paper
• Core — 4× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Instructional Manipulation Check — 3× in this paper
• Abstraction — 2× in this paper · explained in 1 episode
• Cognitive Load — 2× in this paper · explained in 2 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Language Server Protocol — 2× in this paper
• Symposium on Security and Privacy — 2× in this paper
• AI Integration — 1× in this paper · explained in 1 episode
• Abstract Syntax Trees — 1× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Agentic Coding — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Hybrid Approach — 1× in this paper · explained in 4 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Nadia — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Efficient Training of Language Models to Fill in the Middle
• Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
• Qwen3-Coder-Next Technical Report
• Evaluating Large Language Models Trained on Code
• NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
• Qwen2.5-Coder Technical Report
• How Secure is Code Generated by ChatGPT?
• Structured Generative Models of Natural Source Code
• Training language models to follow instructions with human feedback
• Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions
• The Impact of AI on Developer Productivity: Evidence from GitHub Copilot

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs