AARTS

AARTS is a tag in this directory for coverage of AI assurance and risk-testing tools, meaning software that checks whether AI systems behave safely and as intended. Its exact scope should be confirmed against the tagged articles before it is relied on for compliance work. Readers should check the source material to see what the tool does and who runs it. Note: I couldn't verify what "AARTS" stands for or which organization uses it, so this description is a general placeholder. Please replace it with a version based on the actual articles or your editorial definition.

1 item

Corporate PolicyGlobal2026-10-24

Email Prompt Injection Turns Trusted AI Agents Into Attack Tools

Gen Threat Labs published research showing AI agents can be redirected by malicious instructions embedded in ordinary email content, with no software flaw required. Gen Digital responded with the Agent Trust Hub, a layered security framework covering pre-installation scanning, encrypted agent connectivity, and runtime action interception. The accompanying AARTS open specification sets a proposed standard for agent runtime safety that enterprise teams can reference.

Gen Digital prompt injection agentic AI runtime safety agent security AARTS supply chain risk