Relevance As a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling...

CVE-2025-24007

A vulnerability has been identified in SIRIUS 3RK3 Modular Safety System MSS All versions, SIRIUS Safety Relays 3SK2 All versions. Affected devices only provide weak password obfuscation. An attacker with network access could retrieve and de-obfuscate the safety password used for protection again...