When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems

arXiv:2609.10548 · cs.SE, cs.CR · Submitted 2026-06-25 · Read on arXiv

cs.SE, cs.CR

Submitted: 2026-06-25

Updated: 2026-06-25

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

Terminology

• Verification — 3× in this paper · explained in 2 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties