Skill: image-moderate

Version: 1.0.0

Check images for content policy violations using AI moderation.

Returns safety scores and flags.

name: image-moderate version: 1.0.0 description: Check images for content policy violations and safety flags

Credentials

credentials:

• name: OPENAI_API_KEY required: false description: OpenAI API key

Skill inputs

inputs:

• name: image_url type: string required: true description: URL of the image to moderate
• name: policy type: string default: standard enum: [standard, strict] description: Moderation strictness

Skill outputs

outputs:

• name: flagged type: boolean description: Whether content violates policy
• name: categories type: object description: Category flags (violence, sexual, hate, etc.)
• name: scores type: object description: Confidence scores per category
• name: metadata type: object description: Processing metadata

Backend options

backends:

• name: openai type: remote requires: [OPENAI_API_KEY]
• name: ollama type: local models: [llava]

Expanso components used

components: inputs: - stdin - http_server processors: - mapping - openai_chat_completion - log outputs: - stdout - sync_response