Amazon Bedrock

Detection of potential cross-region inference abuse in Amazon Bedrock Claude models, which may indicate attempts to bypass regional security controls or perform unauthorized data processing.

This brief outlines a detection strategy for identifying unusually large prompts sent to AWS Bedrock Claude models, which may indicate prompt injection attacks, data exfiltration attempts, or abuse of the AI service, warranting investigation by detection engineers.

This threat detection rule identifies initial reconnaissance activities within AWS by flagging an IAM principal's first-time invocation of sensitive discovery APIs, such as GetCallerIdentity, ListUsers, ListBuckets, and DescribeInstances, when the originating IP address is associated with consumer VPNs, high-usage hosting providers, or networks linked to threat groups like TeamPCP, indicating an attacker performing enumeration of cloud resources from a suspicious network origin.

A detection rule identifies AWS access key IDs, Amazon Bedrock API keys, PEM private-key blocks, and GitHub/GitLab tokens within Amazon Bedrock model prompts or completions, indicating a critical credential exposure event through misconfiguration, data leakage, or prompt injection that necessitates immediate secret rotation and investigation.

This brief outlines the detection of hostile or aggressive prompt sentiment sent to AWS Bedrock Claude large language models, indicating potential abuse, harassment, or attempts at model manipulation, requiring the configuration of Bedrock model invocation logging and Splunk ingestion.