Detections
Explore public detection logic contributed by the community across SIEM and rule languages.
7,270 detections
Filters
Last updated
All Time
Detection languages
3,342
1,086
505
478
472
Contributors
1,824
1,622
874
505
300
Categories
3,031
2,542
1,076
1,049
929
Platforms
39,960
7,270
6,537
3,868
3,651
Products / Services
1,331
1,109
991
658
494
MITRE Techniques
2,271
1,336
1,318
904
885
CVEs
66
65
33
32
28
IDS Classtypes
81
80
56
27
10
IDS Protocols
149
98
6
5
4
Detects anomalous DNS query patterns originating from AI agent hosts that are characteristic of DNS tunneling, such as the use of TXT or NULL records and excessively long subdomain labels. These techniques are often used by attackers to establish covert Command and Control (C2) channels and exfiltrate data by bypassing traditional HTTP/HTTPS egress filtering.
Detects the presence of a specific, hardcoded Ed25519 public key associated with malicious cross-platform payloads (npm, Go modules, Terraform providers) that use Slack for C2 communication.
Detects malicious JavaScript injection on e-commerce checkout or payment pages designed to harvest sensitive payment card information (PAN, CVV, expiry) and exfiltrate the stolen data to an external endpoint. This behavior is indicative of a digital credit card skimmer (e.g., Magecart style) deployed following a compromise of the web application.
Detects the execution of the Graphalgo RAT second-stage payload. The rule identifies the spawning of a detached 'go run .' process, which performs an ephemeral key exchange using a hardcoded public key before C2 establishment. It also correlates this activity with parent processes common in software build environments (npm, terraform, go) to differentiate malicious staging from developer activity.
Detects an account takeover chain where a device loads a malicious JavaScript component ('load-addon.js') in a browser session, followed by repeated attempts to bypass bot detection mechanisms (targeting Google's 'errors/robot.png') as the payload attempts to force authentication challenges or password resets.
Detects network communication to specific Gusercontent endpoints consistent with malicious browser extensions exfiltrating captured session tokens or cookies. The rule monitors for POST requests containing parameters like leadId, email, and data, often used to transmit stolen authentication material.
Detects execution of package management commands (pip, npm, conda) that attempt to pull packages from registries other than the approved internal repositories. This behavior is indicative of potential AI supply-chain compromise, including malicious packages or namesquatting targeted at machine-learning or LLM-related development workflows.
Detects instances where machine learning runtime processes (e.g., Python, torch-model-loader) load serialized model files (e.g., .pkl, .joblib, .pth) and subsequently spawn suspicious child processes like command shells, scripting engines, or download utilities. This behavior is indicative of arbitrary code execution via unsafe deserialization of a malicious model artifact.
Detects high-volume outbound transfers of sensitive machine learning artifacts, such as model files, training datasets, and model registries, to unauthorized external destinations like personal email or unmanaged cloud storage. This behavior is indicative of potential intellectual property theft.
Detects potential poisoning of machine learning training data by identifying unauthorized file modifications to datasets, DVC repositories, or model registries that occur outside of authorized ETL or CI/CD windows.
This rule detects potential AI/ML supply chain compromise by monitoring for package installations (via pip, conda, poetry, etc.) from non-standard repositories, direct URLs, or version control systems within data science and CI/CD pipelines (e.g., Jupyter, Airflow, Jenkins). It further correlates this activity with subsequent suspicious outbound network connections from the host, which is indicative of slopsquatting or malicious dependency execution.
Detects a sequence of potentially malicious activity involving the bulk reading or downloading of sensitive AI-related artifacts (model files, datasets), followed by the staging of these files into a compressed archive, and finally an outbound network transfer to an external IP address. This behavior pattern is indicative of data exfiltration of intellectual property.
This rule detects the execution of the Cloudflare 'cloudflared' utility from non-standard directory locations. Cloudflared is often abused by threat actors to establish reverse tunnels (e.g., TryCloudflare) to gain unauthorized, persistent, and encrypted external access to a compromised host, effectively bypassing standard perimeter network security controls.
Detects host-side indicators of potential container escapes and unauthorized access, including mounting sensitive container runtime sockets, executing containers with privileged flags, host namespace sharing, and the use of nsenter to break out of a container context.
Detects a chained sequence of suspicious activity initiated by agentic AI development tools (e.g., Claude Code, Aider, AutoGen). The rule identifies the execution of these tools followed by local reconnaissance commands, lateral movement attempts, and outbound network connections originating from the same host, indicating potential automated exploitation or credential abuse.
Detects command-line execution patterns that exhibit hallmark traits of LLM-generated code, such as overly verbose and explanatory comments, appearing alongside common obfuscation or decoding primitives (e.g., base64, iex, eval). This combination suggests the use of AI to assist in creating decoy logic or burying malicious payloads within legitimate-appearing scripts to evade detection.
Detects a chained sequence of suspicious activity initiated by agentic AI development tools (e.g., Claude Code, Aider, AutoGen). The rule identifies the execution of these tools followed by local reconnaissance commands, lateral movement attempts, and outbound network connections originating from the same host, indicating potential automated exploitation or credential abuse.
Detects network communication to specific Gusercontent endpoints consistent with malicious browser extensions exfiltrating captured session tokens or cookies. The rule monitors for POST requests containing parameters like leadId, email, and data, often used to transmit stolen authentication material.
Detects network communication to a suspicious staging domain (pdf.gusercontent.com) that mimics legitimate services. This traffic is associated with the 'onInstalled' event handler of a malicious browser extension, often used to signal a successful infection or initiate secondary payload delivery.
Detects the on-disk presence of a malicious Firefox browser extension, 'pdf-para-texto@extensao.local', used for credential or data harvesting. The rule monitors for the creation of its manifest file or XPI package in specific directories, indicating the staging or installation of the malicious extension.
Detects a multi-stage attack chain where an AI-agent's configuration file (e.g., mcp.json) is modified, followed immediately by the execution of a tool process (node/python) spawned by the agent, the subsequent spawning of a shell process, and finally an outbound network connection to a rare, non-standard domain. This sequence is indicative of AI agent tool poisoning, where malicious tool definitions are introduced to execute arbitrary commands and exfiltrate data. Coverts T1195.002, T1565.001, T1059
Page 42 of 347