venice-image-generate

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents interactions with the official Venice AI API endpoints at api.venice.ai. These are vendor-owned resources essential for the skill's core functionality.
  • [COMMAND_EXECUTION]: The documentation contains curl and Node.js examples for performing API requests. These are standard instructional snippets for developers and do not involve unauthorized system access or privilege escalation.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an interface that takes user-provided prompts and sends them to a remote image generation service. While this represents a functional injection surface, it is standard for generative AI skills, and the documentation highlights the presence of a safe_mode feature at the API level.
  • Ingestion points: 'prompt' and 'negative_prompt' request fields in the provided examples.
  • Boundary markers: No explicit instructions for delimiting user input or ignoring embedded instructions are provided in the skill body.
  • Capability inventory: Network access via curl and fetch to the Venice AI API.
  • Sanitization: The skill relies on the remote API's internal safety mode and content filtering mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:34 PM
Security Audit — agent-trust-hub — venice-image-generate