APEX: Active Protection at Execution Boundaries for LLM Agents

Indirect prompt injection IPI hides adversarial instructions in content that large language model LLM agents read at runtime. As agents compose heterogeneous capability units, including Tools, MCP servers, and Skills, the carriers of injection multiply, and defenses built to recognize attack...

Moderate: Red Hat Security Advisory: jbossas security update

An update for JBoss Enterprise Web Platform 5.1.2 that fixes one security issue is now available from the Red Hat Customer Portal. The Red Hat Security Response Team has rated this update as having moderate security impact. A Common Vulnerability Scoring System CVSS base score, which gives a...