Browse Rules

Search and filter across all detection sources

21 rules

elastic medium kql

OpenAI ChatGPT Enterprise Gmail Message Sent via Connector

Detects ChatGPT Enterprise Gmail connector `send_email` responses. Adversaries who abuse a linked Gmail connector after session compromise can exfiltrate data or perform lateral phishing by sending mail on behalf of the user. Draft-only activity (`create_draft`) is excluded.

elastic medium kql

OpenAI ChatGPT Enterprise Google Drive Download Burst

Detects a ChatGPT Enterprise user downloading five or more distinct Google Drive files through the Drive connector within a one-hour window. Adversaries who abuse a linked Drive connector after session compromise often stage bulk file retrieval before sharing, forwarding, or other exfiltration.

elastic medium kql

OpenAI ChatGPT Enterprise Slack Query Burst

Detects a ChatGPT Enterprise user issuing ten or more distinct Slack app search queries in a five-minute bucket. Adversaries who abuse a linked Slack connector after session compromise often run rapid multi-query searches across channels and messages to locate sensitive content before collection or exfiltration.

elastic medium kql

OpenAI ChatGPT Enterprise Suspicious Gmail Discovery

Detects ChatGPT Enterprise Gmail connector searches that look like sensitive discovery: attachment hunts across multiple document types, or queries matching credential, financial, HR, or legal themes. Attackers abusing a linked Gmail connector after session compromise often search mail for high-value content before exfiltration or send-as abuse.

elastic low kql

First Time GCP Vertex AI Agent Engine Sandbox Code Execution by User and Source ASN

Detects the first time a Vertex AI Agent Engine caller executes code in a sandboxEnvironment from a given source autonomous system. First-time sandbox execution by a user and source ASN can indicate a new workload, stolen credentials used from an unusual network, or early Agent Engine abuse before broader sandbox reuse is visible.

elastic medium kql

OpenAI ChatGPT Enterprise High Codex MCP Tool Diversity

Detects a ChatGPT Enterprise Codex user invoking a high number of distinct MCP tools across multiple connectors within a 30-minute bucket. Broad tool and connector diversity in a short window can indicate compromised-account recon, unauthorized multi-system collection, or an agent rapidly enumerating organizational data sources.

elastic medium kql

OpenAI ChatGPT Enterprise Unusual Codex Plugin Installed

Detects the first ChatGPT Enterprise Codex plugin install for a given plugin display name and plugin name pair within the rule history window. Newly installed Codex plugins expand the tools and data sources available inside agent sessions; adversaries can enable unexpected connectors to persist access to mail, chat, or file systems after initial compromise.

elastic medium kql

OpenAI ChatGPT Enterprise Google Drive Sensitive Query Burst

Detects a ChatGPT Enterprise user issuing five or more distinct Google Drive app search queries in a five-minute bucket where at least one query matches sensitive-data themes (payroll, payslip, confidential, payment, NDA, credentials, and similar). Adversaries who abuse a linked Drive connector after session compromise often run rapid multi-term searches to locate high-value files before download or sharing.

elastic medium eql

GenAI CLI Started with Unsafe Permission Bypass

Identifies GenAI agent CLIs started with permission-bypass or auto-approval flags that disable human-in-the-loop guardrails. These modes are intended for isolated sandboxes but are frequently misused on internet-connected developer workstations, allowing prompt injection, compromised dependencies, or malicious skills to execute commands, modify files, or reach sensitive paths without confirmation.

elastic medium eql

AWS Bedrock High Tool-Request Call Volume

A machine learning job has detected an unusually high number of tool-requesting Amazon Bedrock model responses within 15 minutes for a caller, compared with that caller's own history. High call volume can indicate repeated over-invocation or loop amplification by an AI agent (OWASP ASI02, Tool Misuse and Exploitation) and can lead to resource exhaustion and cost. The volume counts responses that requested tools, not confirmed tool executions.

elastic critical kql

Elastic Defend Alert from GenAI Utility or Descendant

Detects Elastic Defend alerts (behavior, malicious file, memory signature, shellcode) where the alerted process or its direct parent is a GenAI coding or assistant utility (e.g. Cursor, Claude, Windsurf, Cody, Continue, Aider, OpenClaw, Moltbot, Clawdbot, Codeium, Tabnine, GitHub Copilot). Activity from these tools can indicate prompt injection, malicious skills, or supply-chain abuse; this Higher-Order rule helps prioritize such alerts for triage.

elastic medium eql

Execution via OpenClaw Agent

Detects suspicious child process execution from the OpenClaw, Moltbot, or Clawdbot AI coding agents running via Node.js. These tools can execute arbitrary shell commands through skills or prompt injection attacks. Malicious skills from public registries like ClawHub have been observed executing obfuscated download-and-execute commands targeting cryptocurrency wallets and credentials. This rule identifies shells, scripting interpreters, and common LOLBins spawned by these AI agents.

elastic medium kql

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 re

elastic high kql

Potential Destructive AWS CLI Command Executed by GenAI Agent

Identifies a cloud CLI command that destroys infrastructure or identities, such as terminating EC2 instances, removing S3 buckets, or deleting IAM users, when it is spawned by a GenAI coding agent directly or through the agent's shell wrapper. A compromised or prompt-injected agent can be steered into wiping the developer's environment and cloud account using the credentials it already holds, as seen in the malicious Amazon Q Developer for VS Code v1.84.0 release (AWS-2025-015).

elastic high kql

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.

elastic medium eql

AWS Bedrock Unusually Large Tool-Request Batch

A machine learning job has detected an unusually large number of tool requests generated in a single Amazon Bedrock model response for a caller, compared with that caller's own history. Large batches can indicate over-invocation of tools by an AI agent, for example after prompt injection, ambiguous instructions, or unsafe delegation (OWASP ASI02, Tool Misuse and Exploitation). The count is requested operations in the model output, not confirmed tool executions.

elastic medium eql

AWS Bedrock Unusual Tool Selection

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.

elastic low eql

GenAI or MCP Server Child Process Execution

Detects child process execution from GenAI tools or MCP (Model Context Protocol) servers. Adversaries exploit AI agents to execute system commands, exfiltrate data, or establish persistence. MCP servers provide LLMs direct access to execute shell commands, read files, and interact with external services. This building block provides visibility into AI-initiated process execution for correlation with other suspicious activity.

elastic medium kql

OpenAI ChatGPT Enterprise Unusual MCP App Activity

Detects the first time a ChatGPT Enterprise MCP app name is used by a given user email within an organization in the rule history window. MCP apps connect ChatGPT to external systems and can move organizational data into third-party tools. Alerting on first-seen organization, user, and app id triples highlights new or unexpected connector usage rather than every routine approved MCP request. App name is still required in the query for investigation context.

elastic medium kql

AWS Bedrock AgentCore Gateway Tool Invocation Failure Burst

Identifies a burst of failed tool invocations against a single AWS Bedrock AgentCore Gateway within a short window. Individual tool calls fail routinely from bad input or transient upstream errors, but a concentrated run of failures against one gateway can indicate an attacker, or a compromised tool wrapper, probing a tool's parameter surface for an injection point, an authorization bypass, or a schema weakness. Failures can be attributed only to the gateway, not to a specific tool, target, or c

elastic medium eql

GenAI Process Compiling or Generating Executables

Detects when GenAI tools spawn compilers or packaging tools to generate executables. Attackers leverage local LLMs to autonomously generate and compile malware, droppers, or implants. Python packaging tools (pyinstaller, nuitka, pyarmor) are particularly high-risk as they create standalone executables that can be deployed without dependencies. This rule focuses on compilation activity that produces output binaries, filtering out inspection-only operations.