https://taxonomy.eticas.ai/risk/tool-use-risks
Maturity: emerging
AI systems that interact with external tools, APIs, or services, creating unintended side effects or security exposures.
This subcategory is emerging. It has not yet been validated through established assessment methods.
System type: Large language models (LLM)
Lifecycle stages: Post Processing
| Framework | Reference |
|---|---|
| AIUC-1 — AI Underwriting Company Standard | Prevent unauthorized AI agent actions (tool-call safety) |