Browse Rules

Search and filter across all detection sources

60 rules

elastic medium kql

GCP Vertex AI High Request and Token Volume

Detects a high number of Vertex AI prompt-response log rows and high total token usage for one model in the lookback window. Totals use provider usage_metadata.total_token_count (includes thinking tokens when billed). High request and token volume can indicate model extraction, quota abuse, or a compromised caller. Tune thresholds for your baseline.

elastic medium kql

GCP Vertex AI Publisher Model Config Modified

Detects changes to Vertex AI publisher model configuration via SetPublisherModelConfig (for example enabling or retargeting prompt/response BigQuery logging). Unexpected config changes can disable security-relevant logging or redirect logs.

elastic medium kql

GCP Vertex AI Elevated Safety Rating on Response

Detects Vertex AI prompt-response logs where a candidate safety_ratings.probability is HIGH or MEDIUM. Those values are stronger signals than NEGLIGIBLE or LOW alone. Requires the request to include safetySettings so ratings are logged.

elastic medium kql

GCP Vertex AI Response Blocked by Safety Filters

Detects Vertex AI GenerateContent responses whose candidate finish_reason is SAFETY. That value is emitted when Gemini safety filters stop generation. Unlike textual refusals (finish_reason STOP), SAFETY means the provider blocked or truncated the completion.

elastic medium kql

GCP Vertex AI Safety Filters Set to BLOCK_NONE

Detects Vertex AI GenerateContent requests that set safety_settings.threshold to BLOCK_NONE. That threshold disables category blocking for the listed harm categories when clients explicitly send safetySettings. Attackers and careless apps use BLOCK_NONE to weaken built-in Gemini filters.

elastic medium kql

GCP Vertex AI High GenerateContent Volume From Single IP

Detects a single source IP making a high number of Vertex AI GenerateContent (or StreamGenerateContent) audit calls against the same model resource in the lookback window. That pattern fits model extraction, automated scraping, or a compromised caller burning prediction quota.

elastic high kql

GCP Vertex AI Prompt or Response Containing Credentials

Detects a GCP Vertex AI GenerateContent exchange whose prompt or model reply contains a known credential pattern (AWS access keys, GitHub tokens, PEM private keys, and similar), or whose assistant reply warns about exposed keys and revocation. Secrets in prompt/response logs are visible to anyone with access to BigQuery prompt-response export and Elastic.

elastic medium kql

GCP Vertex AI Caller Impossible Travel

Detects the same Vertex AI authenticated caller (client.user.email) generating aiplatform audit activity from geographically distant source IPs within a short window at an impossible travel speed. That pattern can indicate a stolen user or service-account credential used from multiple regions. Related: GCP Vertex AI Caller Activity From High Number of Countries covers slower multi-country reuse without a high-speed hop.

elastic medium kql

GCP Vertex AI Jailbreak Prompt Heuristics

Detects Vertex AI GenerateContent prompts that match common jailbreak / instruction-override heuristics (for example ignore previous instructions, DAN or developer mode, unrestricted-AI language, or explicit safety-filter bypass). Typical prompt_response_logs exports do not populate HARM_CATEGORY_JAILBREAK (unlike hate/harassment/dangerous ratings); Model Armor findings remain the preferred first-party jailbreak signal when that API is enabled.

elastic critical kql

GCP Vertex AI Caller Activity From High Number of Countries

Detects Vertex AI authenticated caller activity for the same client.user.email from at least three countries and three source IPs within a four-hour interval. That pattern can indicate stolen user or service-account credentials reused from multiple regions, including VPN or cloud egress and return trips where first and last locations are close.

elastic high kql

GCP Vertex AI Repeated Assistant Refusals

Detects three or more Vertex AI GenerateContent replies in 60 minutes whose assistant text indicates a refusal (cannot fulfill/assist/help/answer, unable to assist, decline the request, against my guidelines, and similar), aggregated by project and model. Prompt-response logs lack a stable caller identity, so this is a project-wide refusal burst signal — pivot to auditlogs for principal/IP attribution.

elastic low kql

First Time GCP Vertex AI Inference by Caller from Source ASN

Detects the first time in 14 days that a Vertex AI caller (user or service account) runs model inference (GenerateContent, StreamGenerateContent, Predict, or RawPredict) from a source autonomous system (ASN). Stolen Google Cloud credentials, including exported service account keys and OAuth tokens, are used for LLMjacking from attacker infrastructure, which shows up as the victim identity calling models from a hosting provider, VPN, or residential proxy network it has never used before.

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

GCP Vertex AI Role Granted to Principal

Identifies an IAM policy change on a Google Cloud project, folder, or organization that grants a Vertex AI role (`roles/aiplatform.*`) to a principal. Vertex AI roles control who can invoke models, deploy endpoints, run agents, and read prompt and training data. An adversary who has gained IAM administration rights can grant a Vertex AI role to an identity they control to keep model access after the original foothold is removed, or to run LLMjacking workloads under the victim's billing. Google-m

elastic medium kql

Unusual Process Modifying GenAI Configuration File

Detects unusual modification of GenAI tool configuration files. Adversaries may inject malicious MCP server configurations to hijack AI agents for persistence, C2, or data exfiltration. Attack vectors include malware or scripts directly poisoning config files, supply chain attacks via compromised dependencies, and prompt injection attacks that abuse the GenAI tool itself to modify its own configuration. Unauthorized MCP servers added to these configs execute arbitrary commands when the AI tool i

elastic medium kql

Potential Azure OpenAI Model Theft

Monitors for suspicious activities that may indicate theft or unauthorized duplication of machine learning (ML) models, such as unauthorized API calls, atypical access patterns, or large data transfers that are unusual during model interactions.

elastic medium eql

GenAI Process Connection to Suspicious Top Level Domain

Detects when GenAI tools connect to domains using suspicious TLDs commonly abused for malware C2 infrastructure. TLDs like .top, .xyz, .ml, .cf, .onion are frequently used in phishing and malware campaigns. Legitimate GenAI services use well-established domains (.com, .ai, .io), so connections to suspicious TLDs may indicate compromised tools, malicious plugins, or AI-generated code connecting to attacker infrastructure.

elastic medium kql

GenAI Process Connection to Unusual Domain

Detects GenAI tools connecting to unusual domains on macOS. Adversaries may compromise GenAI tools through prompt injection, malicious MCP servers, or poisoned plugins to establish C2 channels or exfiltrate sensitive data to attacker-controlled infrastructure. AI agents with network access can be manipulated to beacon to external servers, download malicious payloads, or transmit harvested credentials and documents.

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 kql

Microsoft Foundry Keys or Connection Secrets Accessed by New Principal

Identifies the first time in seven days that a high-privilege Azure principal lists or regenerates the API keys of a Microsoft Foundry (Azure AI Services) account, or reads the stored secrets of a Foundry account or project connection. Account keys grant direct inference access to every model deployment on the account and bypass Entra ID conditional access, and connection secrets hold credentials for downstream services such as Azure OpenAI, storage, and search. A compromised identity retrieving

elastic low kql

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

elastic medium eql

Connection to Common Large Language Model Endpoints

Identifies DNS queries to known Large Language Model domains by unsigned binaries or common Windows scripting utilities. Malwares may leverage the capabilities of LLM to perform actions in the affected system in a dynamic way.

elastic critical kql

AWS Bedrock Model Invocation From High Number of Countries

Detects a single AWS principal invoking Amazon Bedrock models from three or more countries and three or more source IPs within the lookback window. LLMjacking operators often distribute stolen AWS credentials across proxies or resell them to multiple buyers, which produces inference traffic for one identity from many unrelated locations.

elastic low kql

Azure OpenAI Insecure Output Handling

Detects when Azure OpenAI requests result in zero response length, potentially indicating issues in output handling that might lead to security exploits such as data leaks or code execution. This can occur in cases where the API fails to handle outputs correctly under certain input conditions.

elastic medium kql

AWS Bedrock Provisioned Model Throughput Tampering

Detects creation, modification, or deletion of AWS Bedrock Provisioned Model Throughput via the CreateProvisionedModelThroughput, UpdateProvisionedModelThroughput, and DeleteProvisionedModelThroughput APIs. Provisioned Throughput reserves dedicated, billed model capacity for Amazon Bedrock. An adversary who scales this capacity up can drive large, unauthorized cost (cloud resource/bill hijacking), while deleting reserved throughput can cause denial of service to production workloads that depend