safety security
The Harm Appeared Between Otherwise Ordinary Tools
X-AgentRed searches service dependencies for risky combinations that a single-tool test can miss.
Summary
X-AgentRed searches service dependencies for risky combinations that a single-tool test can miss.
Personal agents can carry consequences from one service into another while fulfilling an ordinary request. X-AgentRed builds a graph of tool effects and execution preconditions, then uses feedback to explore and refine harmful cross-service paths. Across four frontier agentic models, its authors report 1.77 times the harmful-path rate of the STAC baseline and 2.99 times average tool coverage. This is an evaluation framework for discovering combinations of failures, not a count of incidents in production. The study argues that testing tools one at a time can leave their interactions underexplored.
Why it matters
X-AgentRed searches service dependencies for risky combinations that a single-tool test can miss.
Limits and context
- This is an evaluation framework for discovering combinations of failures, not a count of incidents in production.
Key claims
X-AgentRed searches service dependencies for risky combinations that a single-tool test can miss.
Qualification: This is an evaluation framework for discovering combinations of failures, not a count of incidents in production.
Evidence: source-2026-10-12-007
Sources
- arXiv preprint 2610.13886, original v1arXiv / submitting research authors · primary research
Corrections
: Publication note: The October 12, 2026 edition was prepared and published late on October 12 after the scheduled newsroom task could not start. The edition retains its October 12 date and 9:00 AM America/Detroit reveal time. Reports use sources available before that cutoff; actual preparation and image-generation times are preserved in the provenance records.