FIELD NOTES TOPIC
llm-based agent systems
2 notes, newest first.
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
Researchers propose ColluSkill, a framework for multi-skill attacks that can bypass individual skill checks in LLM-based agent systems. These attacks are composed of locally plausible behaviors that collectively form…
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
Researchers propose ColluSkill, a framework for creating multi-step attacks on LLM-based agent systems. These agents have vulnerabilities in their skill systems that current defenses don't fully address, particularly…
