Skills
Navigate
skills/veniceai/skills/venice-image-edit/Gen Agent Trust Hub

venice-image-edit

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The documentation includes curl command examples to demonstrate how to interact with the Venice AI API endpoints.
  • [INDIRECT_PROMPT_INJECTION]: The API endpoints ingest untrusted data through text prompts and external image URLs.
  • Ingestion points: untrusted data enters via the prompt, image, and image_url fields in API requests as described in SKILL.md.
  • Boundary markers: None described for text prompts.
  • Capability inventory: The skill facilitates image transformations (editing, upscaling, background removal) via the Venice AI service.
  • Sanitization: The API supports a safe_mode parameter (defaulting to true) to filter or blur adult content in the generated images.
  • [EXTERNAL_DOWNLOADS]: The skill describes functionality that allows the Venice AI service to fetch image data from user-provided HTTPS URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 03:39 AM