Can Benign Skills Induce Misaligned Behavior in LLM Agents?
cs.CR
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
- Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
- ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning
- AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
- Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Agent Workflow Memory
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
- Agent-SafetyBench: Evaluating the Safety of LLM Agents
- SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data