skills/runcomfy-com/skills/video-edit/Gen Agent Trust Hub

video-edit

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the @runcomfy/cli command-line tool to execute video editing tasks by routing user requests to specified AI models via the runcomfy run command.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided prompts and media URLs, which serves as a surface for indirect prompt injection.\n
  • Ingestion points: The skill ingests prompt, video, reference_image, image, and video_url parameters within the routing logic defined in SKILL.md.\n
  • Boundary markers: The skill includes a dedicated 'Security & Privacy' section that explicitly warns users to treat external media URLs as untrusted due to potential injection risks.\n
  • Capability inventory: The skill relies on the local runcomfy CLI to submit video processing jobs to remote APIs and download the results.\n
  • Sanitization: The skill documentation specifies that the CLI handles input as a JSON string via the --input flag to prevent shell expansion vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:16 AM
Security Audit — agent-trust-hub — video-edit