Every action below is available as a verb in Cerebral OS — callable from a Cerebral, a Map, or the Runtime API. All executions are governed, audited, and dry-run safe.
Analyze Batch
picdefense:analyze_batch
Analyze multiple images in a single batch request for better efficiency.
Write
Medium risk
Analyze Image
picdefense:analyze_image
Analyze an image for inappropriate content, violence, nudity, and other safety concerns.
Write
Medium risk
Analyze With Policy
picdefense:analyze_with_policy
Analyze an image using a specific custom policy instead of default rules.
Write
Medium risk
Create Policy
picdefense:create_policy
Create a custom content moderation policy with specific rules and thresholds.
Write
Medium risk
Delete Policy
picdefense:delete_policy
Permanently delete a content moderation policy. This action cannot be undone.
Write
High risk
Get Analysis
picdefense:get_analysis
Retrieve the results of a previous image analysis by ID.
Read
Low risk
Get Batch
picdefense:get_batch
Get the status and results of a batch analysis job.
Read
Low risk
Get Policy
picdefense:get_policy
Retrieve a specific content moderation policy by ID.
Read
Low risk
List Analyses
picdefense:list_analyses
List recent image analyses with optional filtering and pagination.
Read
Low risk
List Policies
picdefense:list_policies
List all content moderation policies with optional filtering.
Read
Low risk
Update Policy
picdefense:update_policy
Update an existing content moderation policy.
Write
Medium risk