Detections
Explore public detection logic contributed by the community across SIEM and rule languages.
2,982 detections
Filters
Last updated
All Time
Detection languages
1,486
513
403
239
167
Contributors
986
658
304
198
109
Categories
916
822
673
590
452
Platforms
39,932
7,263
6,535
3,865
3,643
2,982
Products / Services
1,229
703
443
309
200
MITRE Techniques
1,053
824
459
384
348
CVEs
17
16
16
10
10
IDS Classtypes
24
7
7
4
3
IDS Protocols
49
1
Detects an AI agent identity accessing an unusually high number of distinct internal repositories, such as wikis, ticketing systems, code repositories, or customer data stores within a 15-minute window. This behavior is consistent with automated discovery or collection (T1213) by an AI agent.
Detects AI agents attempting to disable or bypass security guardrails, approval gates, or content filters. Additionally, it identifies high-risk or destructive actions taken by an AI agent that lack the required preceding human-approval audit record.
Detects anomalous behavior by an AI agent identity by monitoring for off-hours activity, significant statistical spikes in task invocation volumes compared to a 30-day baseline, or the execution of task categories not previously associated with that specific agent. Such behaviors may indicate account hijacking or unauthorized command injection.
Detects attempts to bypass AI agent safety guardrails by using obfuscated payloads (Base64/hex) or known jailbreak/roleplay trigger phrases. The rule specifically monitors sequences where an initial prompt is blocked by safety filters and is immediately followed by a structurally similar, potentially re-encoded prompt that is subsequently allowed, indicating an active filter evasion attempt.
Detects potential poisoning of an AI agent's RAG knowledge base or vector store through suspicious bulk ingestion or injection of imperative instruction-style content. The rule correlates these ingestion events with subsequent anomalous tool usage patterns by the same agent session, indicating a possible prompt injection or data manipulation attack aimed at altering agent behavior.
This rule monitors for unauthorized changes to GitHub Actions workflows that involve release or publishing processes, specifically looking for indicators of supply chain compromise like the introduction of 'id-token: write' or changes to publish scripts. It correlates these modifications with subsequent workflow executions and npm registry publish events attributed to the same actor to identify potential account takeover and malicious package distribution.
Detects anomalous AI inference API activity characterized by high request volume and high input diversity (querying a wide range of input space). This behavior is indicative of a model replication or extraction sweep aimed at exfiltrating model characteristics or intellectual property.
Detects instances where an AI agent tool invocation contains potential credential data (API keys, tokens) followed by a suspicious sign-in or Key Vault access event from an atypical location for that specific identity within a short timeframe. This rule monitors for potential exfiltration or abuse of credentials handled or exposed by AI agents.
Detects external email or chat messages containing markers typical of Large Language Models (LLMs) combined with urgent language soliciting sensitive information, such as credentials or financial details. The rule correlates these findings with messages from domains that have been recently observed in the environment, indicating potential automated, personalized social engineering campaigns.
This rule monitors for suspicious activity related to AI service accounts and API keys. It detects potential account or key compromise by identifying impossible travel sign-ins coupled with AI API usage, simultaneous usage of a single API key from multiple disjoint network locations, and sudden, high-volume activity from previously dormant service account API keys.
Detects unauthorized modifications or non-pipeline uploads to an ML model registry. The rule flags events where model artifacts lack valid signatures, fail checksum verification, or are uploaded/promoted by non-authorized identities or without required CI/CD provenance, indicating potential ML model backdooring or poisoning.
Detects attempts to bypass LLM safety alignment by utilizing roleplay or hypothetical framing (e.g., DAN mode) alongside evidence of prompt iteration, identified by repeated moderation blocks within the same session.
Detects LLM input containing known instruction-override patterns (e.g., 'ignore previous instructions', 'DAN' jailbreak) paired with requests for privileged system operations, indicating a malicious attempt to bypass guardrails and gain unauthorized control over the LLM model.
Detects LLM input containing known instruction-override patterns (e.g., 'ignore previous instructions', 'DAN' jailbreak) paired with requests for privileged system operations, indicating a malicious attempt to bypass guardrails and gain unauthorized control over the LLM model.
Detects anomalous access patterns to machine learning model inference endpoints, including unauthorized access attempts such as credential failures, scope violations, and quota exhaustion, indicating potential misuse or compromise of private model APIs.
Detects anomalous, exploratory query patterns by an API key or service account against an AI model inference API. High distinct resource access volume in a short timeframe, potentially combined with off-hours activity, indicates reconnaissance phases such as output-ontology or model-family enumeration, which may precede adversarial-example crafting or verification attempts.
This rule detects a multi-stage attack correlation where a user receives multiple inbound emails flagged for high likelihood of being LLM-generated (and containing urgency/credential-harvesting language) and subsequently performs a voice or video authentication attempt that is flagged by deepfake detection systems with a low confidence score, indicating a potential impersonation attempt.
This rule detects successful user logins from multiple geographical locations (impossible travel) where multi-factor authentication (MFA) was not utilized. This behavior is indicative of credential theft or account takeover attempts.
Detects instances where a user account consents to an OAuth application requesting high-privilege or sensitive scopes such as Mail.Read, Files.ReadWrite.All, or offline_access. This behavior is a common indicator of consent phishing attacks, where adversaries trick users into granting persistent access to their cloud resources via malicious OAuth applications.
This rule detects a multi-stage Business Email Compromise (BEC) attack involving executive impersonation via look-alike domains, followed by the creation of suspicious inbox rules (forwarding/deletion) by the victim, and concurrent external communication (Teams/Zoom meeting invites) from a newly created account. It correlates these activities to identify sophisticated payment fraud campaigns.
This rule detects a multi-stage Business Email Compromise (BEC) attack involving executive impersonation via look-alike domains, followed by the creation of suspicious inbox rules (forwarding/deletion) by the victim, and concurrent external communication (Teams/Zoom meeting invites) from a newly created account. It correlates these activities to identify sophisticated payment fraud campaigns.
Page 27 of 142