creativeclaw-plan-video
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows established patterns for AI agent extensions, using MCP (Model Context Protocol) to connect to a remote service hosted on the vendor's domain (creativeclaw.co).
- [SAFE]: Instructions include proactive safety guidelines, such as explicitly forbidding the transmission of private data, local paths, or information about other plugins.
- [SAFE]: Analysis of the extensive reference documentation found no evidence of prompt injection, obfuscation, or remote code execution. All external links point to legitimate service documentation and official platforms like Claude.ai.
- [SAFE]: No use of dynamic context injection (!command syntax) or persistence mechanisms was found in the skill definitions.
Audit Metadata