image-outpainting
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows established security best practices for AI agents. It includes a dedicated security section that identifies potential risks like indirect prompt injection and provides clear mitigation strategies for the agent. Documentation of local token storage (~/.config/runcomfy/token.json) is informational and follows standard CLI practices.\n- [EXTERNAL_DOWNLOADS]: The skill references the @runcomfy/cli package, which is the official command-line interface for the RunComfy service. Installation via standard package managers (npm/npx) is the recommended and safe method.\n- [COMMAND_EXECUTION]: Usage of the bash tool is restricted to the runcomfy command via the allowed-tools configuration. This implements a least-privilege approach, preventing the execution of unrelated or potentially malicious system commands.
Audit Metadata