-
High Confidence Malicious GenAI Assistant Response
Nov 6, 2026 · Domain: Cloud Domain: GenAI Use Case: Security for AI Tactic: Exfiltration Tactic: Defense Evasion Mitre Atlas: AML.T0057 Mitre Atlas: AML.T0054 Data Source: AWS Bedrock Data Source: OpenAI ChatGPT Enterprise Platform: AWS Platform: OpenAI Service: AWS Bedrock Service: OpenAI ChatGPT Enterprise Rule Type: ES|QL Resources: Investigation Guide Resources: LLM ·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.
Read More -
High Confidence Prompt Injection in a GenAI User Message
Nov 6, 2026 · Domain: Cloud Domain: GenAI Use Case: Security for AI Tactic: Execution Tactic: Defense Evasion Mitre Atlas: AML.T0051 Mitre Atlas: AML.T0051.000 Mitre Atlas: AML.T0054 Data Source: AWS Bedrock Data Source: OpenAI ChatGPT Enterprise Platform: AWS Platform: OpenAI Service: AWS Bedrock Service: OpenAI ChatGPT Enterprise Rule Type: ES|QL Resources: Investigation Guide Resources: LLM ·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.
Read More -
This rule correlates alerts from multiple integrations and event categories that involve different user.name values which may represent the same real-world identity. It uses an LLM-based similarity analysis to evaluate whether multiple user identifiers (e.g. naming variations, formats, aliases, or domain differences) likely belong to the same person.
Read More -
This rule correlates multiple endpoint security alerts from the same host and uses an LLM to analyze command lines, parent processes, file operations, DNS queries, registry modifications, module loads and MITRE ATT&CK tactics progression to determine if they form a coherent attack chain. The LLM provides a verdict (TP/FP/SUSPICIOUS) with confidence score and summary explanation, helping analysts to prioritize hosts exhibiting corroborated malicious behavior while filtering out benign activity.
Read More -
This rule correlates multiple security alerts involving the same user across hosts and data sources, then uses an LLM to analyze whether they indicate account compromise. The LLM evaluates alert patterns, MITRE tactics progression, geographic anomalies, and multi-host activity to provide a verdict and confidence score, helping analysts prioritize users exhibiting indicators of credential theft or unauthorized access.
Read More -
LLM-Based Curl Activity Triage
Nov 3, 2026 · Domain: Endpoint OS: Linux OS: macOS OS: Windows Use Case: Threat Detection Tactic: Collection Tactic: Command and Control Tactic: Exfiltration Data Source: Elastic Defend Resources: Investigation Guide Resources: LLM Noise: Medium Performance: Normal Rule Type: ES|QL Platform: Windows Platform: Linux Platform: macOS ·Detects non-allowlisted curl activity on Linux, macOS, and Windows hosts and uses an LLM to assess whether the activity is malicious, benign, or requires investigation. The rule parses and normalizes the destination, redacts sensitive command-line values, and aggregates activity by host and destination before invoking the ES|QL COMPLETION command. Only true positive or suspicious verdicts with confidence above 0.7 generate alerts.
Read More -
Detects non-allowlisted curl activity on Linux hosts via Auditd Manager or Auditbeat and uses an LLM to assess whether the activity is malicious, benign, or requires investigation. The rule parses and normalizes the destination, redacts sensitive command-line values, and aggregates activity by host and destination before invoking the ES|QL COMPLETION command. Only true positive or suspicious verdicts with confidence above 0.7 generate alerts.
Read More -
LLM-Based Wget Activity Triage
Nov 3, 2026 · Domain: Endpoint OS: Linux OS: macOS OS: Windows Use Case: Threat Detection Tactic: Collection Tactic: Command and Control Tactic: Exfiltration Data Source: Elastic Defend Resources: Investigation Guide Resources: LLM Noise: Unknown Performance: Normal Rule Type: ES|QL Platform: Windows Platform: Linux Platform: macOS ·Detects non-allowlisted wget activity on Linux, macOS, and Windows hosts and uses an LLM to assess whether the activity is malicious, benign, or requires investigation. The rule parses and normalizes the destination, redacts sensitive command-line values, and aggregates activity by host and destination before invoking the ES|QL COMPLETION command. Only true positive or suspicious verdicts with confidence above 0.7 generate alerts.
Read More -
Detects non-allowlisted wget activity on Linux hosts via Auditd Manager or Auditbeat and uses an LLM to assess whether the activity is malicious, benign, or requires investigation. The rule parses and normalizes the destination, redacts sensitive command-line values, and aggregates activity by host and destination before invoking the ES|QL COMPLETION command. Only true positive or suspicious verdicts with confidence above 0.7 generate alerts.
Read More -
Lure-Themed Internet-Delivered RMM Executable
Identifies an Internet-delivered remote monitoring and management (RMM) executable whose filename disguises it as a document, invitation, or another company's application. Attackers may use that lure, often through social engineering, to gain remote access to the endpoint.
Read More