image-to-video

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for executing the runcomfy run CLI command. It maps user intent to specific model identifiers and passes parameters as a JSON object to the local shell.
  • [EXTERNAL_DOWNLOADS]: The documentation directs the user to install the @runcomfy/cli package from the NPM registry. It also describes the process of downloading generated video outputs from the runcomfy.net and runcomfy.com domains, which are the official infrastructure for the service.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from external sources.
  • Ingestion points: External data enters the agent context via image_url, video_url, audio_url, and the user-provided prompt field in SKILL.md.
  • Boundary markers: Data is encapsulated within a JSON string provided to the --input flag, which acts as a structural delimiter.
  • Capability inventory: The skill has the capability to execute shell commands via the runcomfy CLI as described across all model routes in SKILL.md.
  • Sanitization: The skill documentation explicitly states that the CLI does not perform shell-expansion on the prompt content, reducing the risk of direct command injection from the prompt text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 07:50 AM