Artificial Intelligence #ai#security
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
New research from arXiv introduces Skill Composition Risk (SCR) and the SCR-Bench benchmark, revealing that LLM agent skills evaluated as safe in isolation can become harmful when composed in multi-step tasks. Attack success rates jump from near zero to over 96% in certain compositions, challenging current security vetting practices.
Jun 17, 2026 2 sources