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
20,443
11,831
5,875
5,151
4,864
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 an abnormally high frequency of tool/function invocations by an AI agent within a one-minute timeframe. This pattern is indicative of a potential hijack where an attacker forces the agent into a runaway loop to perform resource exhaustion (DoS), repetitive brute-force operations, or automated exfiltration of sensitive data via manipulated tool execution.
Detects unauthorized attempts to disable, reconfigure, or bypass AI safety guardrails and moderation services, particularly when followed by high-risk tool invocations such as file deletion, network egress, or credential access. This activity indicates an attacker attempting to impair an AI agent's defensive mechanisms to facilitate malicious actions.
Detects anomalous AI agent behavior where the agent ingests untrusted external content (e.g., tool outputs, RAG retrievals, or web fetches) and subsequently invokes high-risk or sensitive capabilities (such as shell execution, secret reading, or unauthorized network calls) within the same session. This pattern is indicative of an indirect prompt injection attack attempting to leverage the agent's internal tool-calling mechanisms for unauthorized actions.
Detects anomalous AI agent behavior where the agent ingests untrusted external content (e.g., tool outputs, RAG retrievals, or web fetches) and subsequently invokes high-risk or sensitive capabilities (such as shell execution, secret reading, or unauthorized network calls) within the same session. This pattern is indicative of an indirect prompt injection attack attempting to leverage the agent's internal tool-calling mechanisms for unauthorized actions.
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 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.
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.
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 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 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 potential AI model backdoor trigger attempts by identifying inference requests from a single caller that result in high-confidence, rare-label predictions across multiple distinct input artifacts. This pattern is indicative of an adversary probing or activating a poisoned model by injecting specific triggers designed to force anomalous outputs.
Detects unauthorized or unreviewed modifications to AI model weights, retraining jobs, or pushes to the model registry within MLOps pipelines. This activity is monitored to prevent AI model weight poisoning, ensuring that all model-related changes undergo required peer-review or approval processes before deployment.
Detects adversarial evasion attempts against AI-based classification models by identifying inputs that result in a benign or low-risk prediction with confidence scores just below a configured threshold. The detection specifically looks for artifacts that share a hash prefix with previously confirmed malicious samples, indicating a potential iterative perturbation technique used to bypass model boundaries.
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 potential data exfiltration from ML inference APIs by identifying responses to untrusted clients containing patterns indicative of memorized PII (SSN, Email, Credit Card) or detecting automated, repeated extraction-style queries.
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.
Page 12 of 83