A new way to probe personal agents' cross-service risks: sampling a tool-dependency graph reaches a 19.2% average harmful path rate
Instead of letting an LLM guess tool combinations from training memory, the red-teaming framework X-AgentRed samples cross-service paths from a tool-dependency graph, reaching a 19.2% average harmful path rate across four frontier agents in a simulated ecosystem of 30 services and 914 tools, above STAC's 10.5% and TRACE's 2.7%.