EXPLORE DETECTIONS
AWS AssumeRoleWithWebIdentity from Kubernetes SA and External ASN
Detects successful `AssumeRoleWithWebIdentity` where the caller identity is a Kubernetes service account and the source autonomous system organization is present but not `Amazon.com, Inc.` EKS workloads that obtain IAM credentials via IAM Roles for Service Accounts (IRSA) normally reach STS from AWS-managed or AWS-associated networks; the same identity from a clearly external ASN can indicate a stolen or misused projected service-account token being exchanged for IAM credentials off-cluster.
AWS Attempt to Leave Organization
Detects any attempt, successful or denied, for a member account to leave an AWS Organization via the LeaveOrganization API. Leaving an organization immediately strips the account of every Service Control Policy (SCP) guardrail the organization enforces, removes it from centralized CloudTrail aggregation, and eliminates the management account's ability to audit or control it going forward. An adversary who has gained root or organization-management-capable access in a member account may use this technique to escape organizational security controls and operate unmonitored. Denied attempts are included because a blocked call is just as strong a signal of intent as a successful one, and is often the only trace left when the account's default permissions correctly prevent the action.
AWS Backup Recovery Point Deleted
Identifies deletion of an AWS Backup recovery point via DeleteRecoveryPoint. A recovery point is a stored backup of a protected resource (EBS, RDS, DynamoDB, EFS, S3, and others). Deleting recovery points removes the ability to restore the associated data and is a core anti-recovery technique used in ransomware and data-destruction attacks to ensure victims cannot recover without paying or rebuilding. Routine lifecycle expirations are performed by the AWS Backup service itself; deletion by a non-service principal is rare and should be reviewed.
AWS Backup Vault Deleted or Vault Lock Removed
Identifies deletion of an AWS Backup vault or removal of its Vault Lock configuration via DeleteBackupVault or DeleteBackupVaultLockConfiguration. A backup vault stores recovery points, and Vault Lock enforces WORM (write-once, read-many) immutability that prevents recovery points from being deleted before their retention expires. Removing the lock defeats the primary control designed to stop ransomware from destroying backups, and deleting the vault removes the backup container entirely. Both actions are strong anti-recovery signals and are rare in normal operations.
AWS Batch Job Submitted with Container Override by Unusual Identity
Detects the first time an AWS identity submits an AWS Batch job with a container command override ("containerOverrides.command"), indicating a runtime-modified execution environment. Command overrides allow the submitter to replace the default command of a job definition at submission time. This flexibility is commonly abused by adversaries to inject malicious commands or exfiltration logic into otherwise legitimate Batch compute environments without modifying the underlying job definition — making the malicious activity harder to detect through configuration review alone.
AWS Bedrock Agent Created by IAM User or Root
Identifies AWS Bedrock Agent creation performed directly by an IAM user or the root account. Bedrock Agents are autonomous AI systems that execute multi-step tasks, invoke Lambda action groups to call external APIs, and query knowledge bases. Adversaries with access to an AWS account can create rogue agents configured to exfiltrate data via action group Lambda functions, pivot to other services, or act as a persistent AI-driven command-and-control channel. This rule is scoped to IAMUser and Root identity types — AssumedRole sessions (which represent automated CI/CD pipelines and SSO-federated engineers) are excluded to avoid global false positives from legitimate deployment automation that varies widely across customer environments.
AWS Bedrock Agent or Action Group Manipulation
Detects modification of deployed Amazon Bedrock agents and their action groups, collaborators, or aliases via the Bedrock Agent control plane. Adversaries with access to an AWS account can tamper with an existing, trusted agent by altering its instructions (UpdateAgent), adding or changing action groups that wire the agent to Lambda functions or APIs (CreateAgentActionGroup, UpdateAgentActionGroup), attaching or modifying collaborators (AssociateAgentCollaborator, UpdateAgentCollaborator), or repointing an alias to a tampered version (CreateAgentAlias, UpdateAgentAlias). A PrepareAgent call is required to make a tampered configuration live. By implanting malicious behavior into an agent that legitimate users continue to invoke, an attacker can maintain durable access through a trusted component. Creation of brand-new agents (CreateAgent) is intentionally excluded as lower-signal activity.
AWS Bedrock AgentCore Execution Role Used Outside Its Runtime
Identifies an Amazon Bedrock AgentCore execution role (an AssumedRole identity whose role name begins with "AgentCore-" or contains "BedrockAgentCore") making an AWS API call to a service it has not previously called. AgentCore runtimes normally interact only with Bedrock inference, AgentCore data-plane, and observability services (CloudWatch Logs, X-Ray, CloudWatch metrics), so an execution role suddenly calling STS, EC2, IAM, Secrets Manager, or other services is a strong indicator that the role's temporary credentials were exfiltrated from the agent's microVM (for example, via the Code Interpreter instance-metadata-service credential theft) and are being used outside the runtime for reconnaissance, privilege escalation, or lateral movement. Because the stolen credentials are recorded in CloudTrail under the execution role's own identity, the anomalous service usage, not the identity, is the detectable signal.
AWS Bedrock AgentCore Resource Created with IAM Execution Role
Detects the creation of an AWS Bedrock AgentCore resource (code interpreter, agent runtime, browser, or harness) with an IAM execution role attached. When an attacker with iam:PassRole permission creates an AgentCore resource and attaches a privileged role, subsequent invocations inside that resource execute as the attached role — enabling privilege escalation to roles that trust bedrock-agentcore.amazonaws.com.
AWS Bedrock AgentCore Runtime Prompt Containing Credentials
Identifies prompts sent to an Amazon Bedrock AgentCore runtime that contain AWS access key identifiers (AKIA long-term or ASIA temporary/STS), Amazon Bedrock API keys (ABSK bearer tokens), or PEM-encoded private keys. The runtime application logs record the caller-supplied prompt; credentials embedded in a prompt are exposed to the model provider, persisted in observability logs, and may be returned in completions or used by downstream tools. This commonly indicates accidental secret leakage by a user or application, or an attempt to stage credentials for misuse through the agent. Secrets should never be passed to an agent in clear text.
AWS Bedrock AgentCore Runtime Prompt Targeting Credentials or Instance Metadata
Identifies prompts sent to an Amazon Bedrock AgentCore runtime that attempt to harvest credentials or coerce the agent into exfiltrating data. The runtime application logs capture the caller-supplied prompt; this rule flags prompts that reference the cloud instance metadata service (169.254.169.254, the ECS task metadata address, or the "latest/meta-data" / "security-credentials" paths), prompts that name AWS access or secret keys directly, and prompt-injection or jailbreak language ("ignore previous instructions", "developer mode", "do anything now") combined with intent to reveal secrets, system prompts, or send data to an external endpoint. Asking an agent to read instance metadata credentials or to exfiltrate secrets is rarely legitimate and indicates an attempt to weaponize the agent for credential theft, even when the model refuses the request.
AWS Bedrock API Key Phantom User Activity Outside Bedrock
Identifies an Amazon Bedrock API key phantom user (an IAM user whose name starts with "BedrockAPIKey-") acting as the caller of a non-Bedrock API request, such as IAM, STS, EC2, VPC, or KMS calls. These users are provisioned by AWS to back a Bedrock bearer token and carry the AmazonBedrockLimitedAccess managed policy, which also grants IAM, VPC, and KMS reconnaissance. A phantom user performing activity outside of Bedrock indicates its credentials are being used beyond their intended scope, which is the privilege-escalation path realized: an attacker who created standard IAM access keys for the phantom user is now using them for reconnaissance or lateral movement outside the Bedrock authentication boundary.
AWS Bedrock API Key Used for Destructive or Anti-Recovery Action
Identifies an Amazon Bedrock API key (bearer token) being used to perform a destructive or anti-recovery control-plane action, such as deleting a guardrail, deleting a custom or imported model, removing provisioned throughput, or disabling model invocation logging. Bedrock API keys are bearer credentials intended for model invocation (InvokeModel, Converse); using one to delete Bedrock resources or disable logging is inconsistent with that purpose and is characteristic of LLMjacking or sabotage following key theft. Every Bedrock API key call is identifiable in CloudTrail by "additionalEventData.callWithBearerToken" being true. The rule matches regardless of outcome, because a destructive attempt via a bearer token is suspicious even when denied.
AWS Bedrock Automated Reasoning Safety Policy Tampering
Detects deletion or modification of AWS Bedrock Automated Reasoning policies via the DeleteAutomatedReasoningPolicy, UpdateAutomatedReasoningPolicy, or UpdateAutomatedReasoningPolicyAnnotations CloudTrail actions. Automated Reasoning policies are a Bedrock safety and validation control that constrains model outputs against formal rules. An adversary who deletes a policy or alters the policy definition or its annotations weakens an enforced output-validation defense, potentially allowing unsafe or non-compliant model responses to pass unchecked. Benign build, test-workflow, and test-case CRUD operations are intentionally excluded as they have no coherent abuse path.
AWS Bedrock Detected Multiple Attempts to use Denied Models by a Single User
Identifies multiple successive failed attempts to use denied model resources within AWS Bedrock. This could indicated attempts to bypass limitations of other approved models, or to force an impact on the environment by incurring exhorbitant costs.
AWS Bedrock Detected Multiple Validation Exception Errors by a Single User
Identifies multiple validation exeception errors within AWS Bedrock. Validation errors occur when you run the InvokeModel or InvokeModelWithResponseStream APIs on a foundation model that uses an incorrect inference parameter or corresponding value. These errors also occur when you use an inference parameter for one model with a model that doesn't have the same API parameter. This could indicate attempts to bypass limitations of other approved models, or to force an impact on the environment by incurring exhorbitant costs.
AWS Bedrock Foundation Model Access Enabled or Entitlement Granted
Identifies when access to an Amazon Bedrock foundation model is enabled at the account level, either by granting a foundation-model entitlement, submitting a use case for model access, or creating a foundation-model agreement (accepting the EULA). These account-level "model access" actions unlock a foundation model so that it can subsequently be invoked. Adversaries or a compromised principal may enable model access to abuse expensive models (LLMjacking), to establish a durable ability to invoke models within the account, or to bypass organizational controls. This activity is distinct from changes to a resource-based model invocation policy and is identified by the Bedrock control-plane API calls that grant model entitlements and agreements.
AWS Bedrock Foundation Model Enumeration Followed by Invocation via Long-Term Key
Detects when an AWS principal using long-term IAM user credentials (AKIA* access key) enumerates available Bedrock foundation models and then invokes a model within the same 15-minute window. Most legitimate Bedrock workloads run under IAM roles with short-lived credentials; the combination of model enumeration followed by direct model invocation from a long-term IAM user key is unusual in production environments and consistent with an adversary using stolen credentials to discover and exploit available AI model capabilities. This pattern is associated with LLMjacking attacks where threat actors abuse compromised cloud credentials to run high-volume or high-cost model inference at the account owner's expense.
AWS Bedrock Guardrail Deleted or Weakened
Detects deletion, weakening, or version management of AWS Bedrock guardrails via the DeleteGuardrail, UpdateGuardrail, DeleteEnforcedGuardrailConfiguration, or PutEnforcedGuardrailConfiguration APIs. Bedrock guardrails enforce content, topic, word, and sensitive-information policies on model invocations. Deleting a guardrail, loosening its policies, removing or overwriting the organization-enforced guardrail configuration, or creating a new version to enforce a weakened configuration allows an adversary to bypass these protections — the cloud control-plane equivalent of disabling a security tool. This activity should be validated against approved change management and the responsible identity.
AWS Bedrock Guardrails Detected Multiple Policy Violations Within a Single Blocked Request
Identifies multiple violations of AWS Bedrock guardrails within a single request, resulting in a block action, increasing the likelihood of malicious intent. Multiple violations implies that a user may be intentionally attempting to cirvumvent security controls, access sensitive information, or possibly exploit a vulnerability in the system.
AWS Bedrock Guardrails Detected Multiple Violations by a Single User Over a Session
Identifies multiple violations of AWS Bedrock guardrails by the same user in the same account over a session. Multiple violations implies that a user may be intentionally attempting to cirvumvent security controls, access sensitive information, or possibly exploit a vulnerability in the system.
AWS Bedrock High Risk Filesystem or Execution Tool Invocation
Detects when a Bedrock model is prompted to invoke high-risk tools associated with shell execution, filesystem operations, or process spawning. Adversaries may use compromised AI agent pipelines or manipulated prompts to instruct the model to execute arbitrary system commands, read or write sensitive files, or spawn subprocesses — extending the blast radius of a credential compromise or prompt injection attack.
AWS Bedrock High-Frequency Single-Model Inference API Probing
Identifies an AWS principal performing a high volume of Amazon Bedrock inference API calls against a single model within a short window. Membership inference attacks require hundreds to thousands of statistically similar queries whose prompts and responses are intentionally content-benign, making guardrail- and content-based rules ineffective. This rule detects the high-frequency single-model probing pattern that precedes membership inference and related exfiltration via the inference API. It is a behavioral / volumetric precursor: it does not observe model confidence scores and a fixed call-count threshold only catches the loud variant, so paced, low-and-slow, or credential-distributed probing will evade it. Definitive membership inference detection requires ML anomaly analysis over per-entity inference-rate and response-distribution baselines.
AWS Bedrock Invocations without Guardrails Detected by a Single User Over a Session
Identifies multiple AWS Bedrock executions in a one minute time window without guardrails by the same user in the same account over a session. Multiple consecutive executions implies that a user may be intentionally attempting to bypass security controls, by not routing the requests with the desired guardrail configuration in order to access sensitive information, or possibly exploit a vulnerability in the system.