Browse Rules

Search and filter across all detection sources

16 rules

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

Unusual High Denied Topic Blocks Detected

Detects repeated compliance violation 'BLOCKED' actions coupled with specific policy name such as 'topic_policy', indicating persistent misuse or attempts to probe the model's denied topics.

elastic medium kql

Unusual High Word Policy Blocks Detected

Detects repeated compliance violation 'BLOCKED' actions coupled with specific policy name such as 'word_policy', indicating persistent misuse or attempts to probe the model's denied topics.

elastic medium kql

Unusual High Denied Sensitive Information Policy Blocks Detected

Detects repeated compliance violation 'BLOCKED' actions coupled with specific policy name such as 'sensitive_information_policy', indicating persistent misuse or attempts to probe the model's denied topics.

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

Unusual High Confidence Content Filter Blocks Detected

Detects repeated high-confidence 'BLOCKED' actions coupled with specific 'Content Filter' policy violation having codes such as 'MISCONDUCT', 'HATE', 'SEXUAL', INSULTS', 'PROMPT_ATTACK', 'VIOLENCE' indicating persistent misuse or attempts to probe the model's ethical boundaries.

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 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 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.

elastic low kql

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.

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

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 kql

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.

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

GenAI Agent Instruction File Written to Downloads

Detects creation or change of an AI coding-agent instruction file (agents.md or claude.md) in a user Downloads folder by a browser or an archive tool. A web page can save AGENTS.md or CLAUDE.md into Downloads without a click, and opening an archive can extract the same files there. Codex and Claude Code treat those files as trusted project instructions, which can lead them to rewrite their own configuration, install a package, or leak a login token.