video-outpainting

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @runcomfy/cli tool from the NPM registry to enable its core functionality.
  • [COMMAND_EXECUTION]: The skill uses the runcomfy CLI tool to execute video processing workflows on the RunComfy platform.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes external content from user-provided URLs.
  • Ingestion points: The video_url parameter in the CLI input JSON (SKILL.md).
  • Boundary markers: Data is passed within a structured JSON object to the CLI command.
  • Capability inventory: The skill utilizes the runcomfy CLI and makes network requests to vendor APIs.
  • Sanitization: The documentation claims the CLI avoids shell-expansion for the input JSON, which serves as a mitigation for direct command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:57 AM
Security Audit — agent-trust-hub — video-outpainting