Harness Matters: Measuring and Dissecting Security Resilience in Web Agents

Summary

This paper measures how the execution harness of web agents affects their security, not just the backend model. The authors model harnesses as four stages (goal interpretation, webpage perception, reasoning and planning, action execution) and build WebTrap Farm, an evaluation framework covering malicious user prompts, malicious prompt injection, and deceptive web design. They find existing harnesses remain vulnerable to typical attacks, with some unsafe behaviors occurring without explicit attack content, and that both harness and backend model significantly affect outcomes.

Related items

• LowHelp defend against memory poisoning in Amazon Bedrock AgentCore with multi-layer write validationSimilar attack · AWS Security Blog
• InfoSuppression Is Not Erasure: Mechanistic Analysis and Reactivation Boundaries of Subspace Projection for LoRA Backdoor DefenseSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoCan the Confidence and Decisions of System 1 Models Be Trusted? An Explainability and Perturbation Audit of Jev-Style Decision ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoAnyBreak: Towards Jailbreaking Any T2I Model for Any ConceptSimilar attack · Arxiv (cs.RO + cs.CV security)
• MediumTop MCP security resources — November 2026Similar attack · Adversa AI Blog