https://taxonomy.eticas.ai/risk/unsafe-tool-calls
Maturity: established
The agent invokes tools, APIs, or services beyond its intended scope — for example, calling the wrong tool, calling a tool with incorrect parameters, or accessing systems it was not designed to interact with.
System type: Large language models (LLM)
Lifecycle stages: Post Processing
| Framework | Reference |
|---|---|
| OWASP Top 10 for Agentic Applications 2026 | ASI02 Tool Misuse and Exploitation |