Skip to main content
Version: 6.1

AI Security: Lookups

The AI Security module uses 11 lookups in two categories: attack signatures and baseline values.

Intended audience: information security analysts and SOC engineers


Signature Lookups

These lookups are used by jobs to detect threats in requests, responses, and agent actions.

LookupPurpose
prompt_injection_patternsSignatures of prompt injection attempts: instruction overrides, role substitution, system prompt extraction, and jailbreaks
llm_warning_keywordsData leakage signatures: access tokens and passwords, personal data, NDA markers, and indicators of web attacks (XSS, SQL injection, and shell injection)
system_prompt_patternsMarkers associated with model system prompts
model_storage_pathsPaths and file extensions for model artifacts, including weights and tokenizers
training_data_pathsPaths and file formats for training datasets
dangerous_agent_actionsSignatures of dangerous commands and actions, including destructive operations and the download and execution of third-party code
agent_process_namesAI agent runtime process names used to associate a detected action with a specific agent

Baseline Lookups

These lookups are used by jobs to detect deviations from expected behavior and serve as allowlists or baselines.

LookupPurpose
agent_permission_baselineBaseline (expected) AI agent permissions: approval mode, network access, allowed prefixes, sandbox mode, and origins
model_storage_authorizedUsers authorized to access model repositories
training_data_authorizedUsers authorized to access training data
agent_known_destinationsNetwork destinations allowed for AI agents
Important

Lookups containing deployment-specific data must be adjusted for the target deployment.