Elastic Security Detection Rules

AWS Bedrock Unusual Tool Selection

Last updated a day ago on 2026-11-06
Created 15 days ago on 2026-10-23

About

A machine learning job has detected that an Amazon Bedrock model requested a tool that is rare for a caller, compared with that caller's own history. A model that suddenly selects an unfamiliar tool can indicate that an AI agent was redirected toward an unexpected capability, for example through prompt injection or unsafe delegation (OWASP ASI02, Tool Misuse and Exploitation). The tool name is a requested operation in the model output, not a confirmed tool execution.
Tags
Domain: GenAIData Source: AWS BedrockPlatform: AWSService: AWS BedrockUse Case: Security for AIRule Type: Machine LearningRule Type: MLTactic: ExecutionMitre Atlas: AML.T0053
Severity
medium
Risk Score
47
False Positive Examples
A newly deployed or newly enabled tool is rare by definition until it has been used regularly. Confirm any recent change to the agent's tool set. Seasonal or rarely used legitimate tools, such as monthly reporting or maintenance tools, can appear unusual when they are used.
License
Elastic License v2(external, opens in a new tab or window)

Definition

Rule Type
Machine Learning
Integration Pack
Prebuilt Security Detection Rules
Related Integrations

security_ai(external, opens in a new tab or window)

aws_bedrock(external, opens in a new tab or window)

Query
text code block:

Install detection rules in Elastic Security

Detect AWS Bedrock Unusual Tool Selection in the Elastic Security detection engine by installing this rule into your Elastic Stack.

To setup this rule, check out the installation guide for Prebuilt Security Detection Rules(external, opens in a new tab or window).