Browse Rules

Search and filter across all detection sources

25 rules

panther medium python

Snowflake Login Without MFA

Detect Snowflake logins without multifactor authentication

elastic medium kql

Microsoft Foundry Jailbreak Detected

Detects a Microsoft Foundry chat, sent through API Management, where Azure sets jailbreak.detected on the prompt. The flag is on the prompt filter when the call is allowed through, and on the error body when the filter blocks the call.

elastic high kql

Microsoft Foundry Repeated Assistant Refusals

Detects three or more completed assistant refusals from the same client, API Management subscription, and model. Matching replies finished on their own (finish_reason stop) and declined the prompt. A burst means that caller kept sending prompts the model will not answer.

elastic medium kql

OpenAI ChatGPT Enterprise Memory Deleted

Detects ChatGPT Enterprise audit events that delete stored memory. Adversaries may delete memory entries to remove evidence of prior prompts, preferences, or staging instructions after misuse.

elastic medium eql

Claude Cowork VM Boot Image Tamper

Detects unexpected modification of Claude Desktop Cowork VM boot images (kernel, initrd, root filesystem). Adversaries with user-context access can rewrite these stored images so later Cowork sessions boot attacker-controlled code inside a virtual instance that host EDR cannot inspect by default.

elastic high kql

High Confidence Prompt Injection in a GenAI User Message

Detects a GenAI user message that a security_ai classifier scores as high-confidence prompt injection. The rule requires a high prediction from one of four models: instruction override, encoding, word obfuscation, or hash string. ES|QL COMPLETION then reviews the message and drops likely false positives before an alert is created.

elastic medium kql

OpenAI ChatGPT Enterprise Workspace Feature Toggled

Detects ChatGPT Enterprise audit events that toggle a workspace feature flag (for example GPT sharing). Adversaries may enable sharing or weaken controls to persist access or broaden data exposure.

elastic medium kql

OpenAI ChatGPT Enterprise Codex Security Scan Configuration Changed

Detects ChatGPT Enterprise Codex security-log events that create or update a repository scan configuration. Changing scan scope, lookback, or notification rules can weaken secrets scanning coverage or redirect findings.

elastic high kql

OpenAI ChatGPT Enterprise Repeated Assistant Refusals

Detects three or more ChatGPT Enterprise assistant messages for the same user whose text matches common policy-refusal phrases (cannot assist, cannot help, cannot fulfill, unable to assist, against my guidelines, and similar) within the lookback window. A refusal burst can indicate jailbreak probing, policy-bypass attempts, or automated unsafe prompting intended to evade model safety controls.

elastic medium kql

OpenAI ChatGPT Enterprise Excessive Conversation Deletion

Detects an unusually high number of ChatGPT Enterprise conversation deletion events for the same user within a rolling 24-hour lookback. Mass deletion can indicate an attempt to remove conversation history or cover tracks after misuse.

elastic medium kql

OpenAI ChatGPT Enterprise Workspace Log File Deleted

Detects ChatGPT Enterprise audit events where a workspace compliance log file is deleted (`delete_workspace_log_file`). Adversaries with privileged access may delete exported audit or conversation log archives to remove evidence from compliance workflows and hinder investigation.

elastic high kql

High Confidence Malicious GenAI Assistant Response

Detects a GenAI assistant response that a security_ai classifier scores as high-confidence malicious content. The rule requires a high prediction from one of four models: refusal, encoding, word obfuscation, or hash string. ES|QL COMPLETION then reviews the response and drops likely false positives before an alert is created.

elastic medium kql

Anthropic Excessive Chat Deletion

Detects an unusually high number of Claude chat deletion events for the same user email within a single calendar day. Mass chat deletion can indicate an attempt to remove conversation history, cover tracks after misuse of Claude, or automated cleanup following data staging or prompt abuse.

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 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 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

OpenAI ChatGPT Enterprise Jailbreak Prompt Heuristics

Detects ChatGPT Enterprise user messages that combine two or more common jailbreak techniques: overriding prior or system instructions, switching the assistant into an unrestricted persona or mode (for example DAN or developer mode), asking it to operate without safety restrictions or filters, or asking it to reveal its system prompt. Jailbreak prompts stack these techniques to talk the model out of its safety policy, and a user doing so in a managed workspace may be attempting to generate prohi

elastic medium eql

Potential Prompt Injection Coercing Shell Execution

Detects shells or scripting interpreters launched from a parent command line that contains common LLM prompt-injection or jailbreak language. Attackers (or malicious content ingested by an agent) use instruction-override, DAN/developer- mode, system-prompt extraction, and safety-filter bypass phrasing to coerce GenAI coding agents and automation wrappers into running attacker-chosen commands. When that injected text reaches a child shell or interpreter, it is a strong signal that untrusted promp

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 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 medium eql

GenAI Process Performing Encoding/Chunking Prior to Network Activity

Detects when GenAI processes perform encoding or chunking (base64, gzip, tar, zip) followed by outbound network activity. This sequence indicates data preparation for exfiltration. Attackers encode or compress sensitive data before transmission to obfuscate contents and evade detection. Legitimate GenAI workflows rarely encode data before network communications.

elastic medium kql

GenAI Prompt Contains Base64-Encoded Payload

Detects base64-encoded content within GenAI prompt or completion text. The security_ai ML model has identified one or more candidate strings in the message that score as encoded payloads. Attackers embed base64 in prompts to smuggle instructions past content filters, exfiltrate data, or inject indirect prompt-injection payloads into model context. Strings that match known credential formats (AWS access key IDs, API keys, private key headers, and similar) are excluded — those fire the dedicated

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 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.

elastic high kql

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