creativeclaw-gemini-omni

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a standard workflow for AI-assisted video generation using the Creative Claw service. All components, including instructions and model references, align with the stated purpose of video production and editing.
  • [EXTERNAL_DOWNLOADS]: The skill references an external tool hosted at app.creativeclaw.co/mcp/chatgpt. This is an official resource from the skill's author (creativeclawco) used for Model Context Protocol (MCP) tool communication, and does not represent an unauthorized external dependency.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied assets such as image_url and video_urls as input for generation tasks. While these are ingestion points for external data, the skill includes specific syntax guidelines and control parameters (e.g., agentic_prompting: false) to manage how the model interprets these inputs. The capability set is limited to multimedia generation and feedback submission.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 12:37 PM
Security Audit — agent-trust-hub — creativeclaw-gemini-omni