Detections
Explore public detection logic contributed by the community across SIEM and rule languages.
1,733 detections
Filters
Last updated
All Time
Detection languages
909
387
164
127
68
Contributors
479
417
201
177
61
Categories
20,453
11,837
5,876
5,154
4,865
1,733
Platforms
822
436
329
274
206
Products / Services
498
378
118
96
79
MITRE Techniques
433
327
225
196
196
CVEs
12
12
10
10
6
IDS Classtypes
1
1
IDS Protocols
2
Detects browser extension updates that request a combination of high-risk permissions capable of account takeover (e.g., cookies, webRequest, identity) for extensions previously classified as low-risk. This pattern often indicates a supply chain compromise where a benign extension is acquired and subsequently updated with malicious capabilities.
Detects the installation or execution of known MALFEX malicious packages via npm or Node.js, which are used as entry points for polyglot or disguised payload delivery.
Detects network exploitation attempts targeting CVE-2026-82329 in JFrog Artifactory. The rule identifies path traversal, malicious Java deserialization payloads, and unauthorized access attempts to sensitive administrative API endpoints.
Detects instances where an AI agent's output contains sensitive credential patterns such as AWS access keys, JWTs, private keys, or Bearer tokens. This rule monitors user communication, generic events, and file creation events to identify potential security compromises or unintended data leakage from the AI model.
This rule detects potentially malicious activity where an identity performs enumeration of Kubernetes secrets or configmaps and subsequently performs a search action within Slack from the same IP address within a one-hour window. This behavioral pattern is indicative of post-breakout reconnaissance, where a compromised identity or token is used to exfiltrate sensitive cloud configuration data and then perform internal reconnaissance in SaaS collaboration tools to identify further targets or credentials.
Detects UNC6240 PSEMHUB.war web shell/tunnel/trojanized installer artifacts by distinctive content markers (x.jsp, u.jsp, tunnel.jsp/jspx, Ple64.exe)
This rule detects potential data exfiltration by monitoring corporate user activities involving consumer generative AI services (e.g., ChatGPT, Gemini, Claude). It identifies suspicious patterns such as large volume submissions, repeated chunked prompts, and the presence of sensitive content (e.g., PII markers, classification labels) or obfuscated payloads (base64/rot13) that suggest an attempt to bypass DLP or detection controls.
This rule detects anomalous, high-volume activity from a single user account interacting with known public generative AI platforms (e.g., ChatGPT, Copilot, Claude). It uses a threshold-based approach on CloudAppEvents logs to identify potential reconnaissance or bulk information gathering activities which could signify unauthorized use or automated data scraping via AI interfaces.
Detects inbound email or ticketing messages containing extortion language (such as payment deadlines, leak-site references, and data-shredding threats) specifically directed at high-value internal targets like executives, security teams, and legal departments. This pattern is consistent with the ShinyHunters 'pay-or-leak' extortion model.
This rule detects potential adversarial reconnaissance activities targeting AI agents via multiple communication channels (e.g., email, collaboration tools). It identifies patterns where a sender transmits messages containing common 'jailbreak' or 'instruction-override' phrases (e.g., 'ignore previous instructions', 'bypass approval') across at least three distinct channels within a 24-hour window, indicating a concerted effort to manipulate or probe agent logic.
This rule detects potential adversarial reconnaissance activities targeting AI agents via multiple communication channels (e.g., email, collaboration tools). It identifies patterns where a sender transmits messages containing common 'jailbreak' or 'instruction-override' phrases (e.g., 'ignore previous instructions', 'bypass approval') across at least three distinct channels within a 24-hour window, indicating a concerted effort to manipulate or probe agent logic.
This rule detects potential adversarial reconnaissance activities targeting AI agents via multiple communication channels (e.g., email, collaboration tools). It identifies patterns where a sender transmits messages containing common 'jailbreak' or 'instruction-override' phrases (e.g., 'ignore previous instructions', 'bypass approval') across at least three distinct channels within a 24-hour window, indicating a concerted effort to manipulate or probe agent logic.
Detects anomalous AI-assisted activity where multiple processes (specifically AI developer tools) appear to be chaining operations by writing to and reading from shared local directories (e.g., 'handoff', 'artifacts') followed by network requests to known AI service APIs. This pattern may indicate automated task chaining or unauthorized exfiltration of context/code to AI platforms.
Detects activity associated with the SharePoint ToolShell exploitation chain, specifically monitoring the w3wp.exe process for spawning suspicious child processes like cmd.exe or powershell.exe, and the creation of unexpected .aspx files within the SharePoint LAYOUTS directory.
Detects evidence of the SCKit supply chain worm within GitHub Actions CI pipelines. The rule identifies attempts to poison the build process by injecting a BASH_ENV path into GITHUB_ENV, which forces the execution of a malicious script (sckit-publish-bridge.sh) during subsequent shell steps. This script is designed to exfiltrate npm publishing credentials (NODE_AUTH_TOKEN) to external infrastructure. The detection logic covers both the injection mechanism and diagnostic output indicators from the bridge script.
Detects anomalous high-volume API requests to machine learning model inference endpoints (e.g., predict, classify, score). This behavior is characteristic of adversarial example crafting, where an attacker sends rapid, near-duplicate requests to estimate gradients or probe confidence scores to manipulate model output.
Detects malicious instruction-override payloads, hidden HTML comments, or obscured text (e.g., zero-font size) in third-party content ingested into LLM/RAG systems, commonly used for indirect prompt injection.
Detects unauthorized or suspicious modifications to machine learning model artifacts within a model registry or deployment pipeline. The rule triggers on detected checksum mismatches, bypassed security/approval workflows, or significant, anomalous deviations in model file size compared to previous versions, which are common indicators of malicious tampering (AML.T0018).
Detects potential ML model-stealing attacks against inference API endpoints. The rule identifies anomalous behavior characterized by an extremely high volume of diverse queries from a single API key over a 24-hour period. Such patterns are consistent with systematic decision-boundary probing or input-space coverage attempts used for training a replica model (distillation or knockoff attacks) without direct access to model weights.
Detects attempts to bypass LLM safety guardrails and system instructions via malicious user prompts containing injection phrases or privilege escalation keywords, which could lead to unauthorized tool execution or sensitive data disclosure.
This rule detects unauthorized or malicious agentic AI behavior where prompt injection or poisoned content causes an AI agent to execute excessive tool calls or enter an infinite loop of tool invocations. This behavior can lead to compute resource exhaustion, increased operational costs, and potential data exfiltration via excessive querying.
Page 8 of 83