Researchers introduced the Agent Incident Registry (AIR), a source-linked catalog of agent-related incidents disclosed from a first date through a last date, with each record carrying supporting evide…
A new security study found that four gatekeeper AI models approved 100 percent of crafted prompts that hid malicious instructions inside ordinary prose, even though each model had blocked the same req…
A new authorization framework called the Agentic Principal Chain (APC) reduces data exfiltration in multi-agent AI systems from 75-100% to 0% across all four AgentDojo domains and blocks all 544 Injec…
An independent researcher found that existing indirect prompt injection benchmarks like BIPIA, InjecAgent, and AgentDojo may produce unreliable scores due to reliance on LLM-judges and evaluation of e…
The Network Intent Layer (NIL) prevents prompt injection in AI agents by making undeclared actions structurally unexpressible, rather than relying on probabilistic filters. In tests against 4,216 inje…