CarryoverBench, a new arXiv benchmark, shows a single injection written into agent memory or heartbeat files re-fires across sessions with no monotonic decay, and that prompt-level defenses mostly act at write time.
CarryoverBench, a new arXiv benchmark, shows a single injection written into agent memory or heartbeat files re-fires across sessions with no monotonic decay, and that prompt-level defenses mostly act at write time.
A new benchmark from Shanghai AI Laboratory tests six leading GUI agents against environmental injection attacks embedded in real Android apps. Every agent is vulnerable, attack success rates reach 66.9%, and stronger agents turn out to be more exploitable, not less.
Tenet Security's DEF CON August 2026 research expands Agentjacking to Cloudflare, Datadog, and Sentry — 90% success rate, DNS hijacking via AI coding agent manipulation, zero traditional exploitation required.
Researchers from Seoul National University, UIUC, and Largosoft introduce Agent Data Injection (ADI) as a distinct attack class that bypasses existing IPI defenses with up to 50% success, targeting the structured metadata and context data agents implicitly trust.
How malicious content in external data sources can hijack agent behaviour in LangChain, LlamaIndex, and AutoGen-style agents via indirect prompt injection through tool responses.