X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems

Evidence record

Read the original source ↗

Claim-level citations (3)

• supportsX-AgentRed explores harmful chains across multiple agent services: X-AgentRed constructs tool-dependency graphs to explore unintended cross-service action chains and improves search using execution feedback.

  Abstract: graph construction and iterative red-teaming method.

• supportsX-AgentRed explores harmful chains across multiple agent services: Across four target agents in a simulated ecosystem, the authors report 1.77 times STAC's harmful-path rate and 2.99 times its tool coverage on average. These ratios use STAC specifically, not an unspecified pooled baseline.

  Introduction; Sections 4.1-4.3; Table 2.

• supportsX-AgentRed explores harmful chains across multiple agent services: The evaluation uses ToolSimulator with 30 services and 914 tools. Claude Opus 4.8 generates tool responses and state updates; Claude Opus 5 and GPT-5.6 Sol act as judges, and each configuration is evaluated in one run.

  Section 4, introductory paragraph; Section 4.1, Environment and Models.