2 papers
cs.SE2026
Characterizing Security Effects of OSS Vulnerabilities in Agent Systems
Yu Ji, Yang Wei, Yutao Hu +3
Software agents increasingly depend on open-source components when executing tools and interacting with external systems. Security flaws in these dependencies may therefore influen…
cs.AI2026
Towards Security-Auditable LLM Agents: A Unified Graph Representation
Chaofan Li, Lyuye Zhang, Jintao Zhai +9
LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. Howev…