imagine

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed around the operation of the vofy-cli command-line tool. It provides specific instructions for the agent to execute shell commands to create media, list tasks, and check account status.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the vofy-cli package via npm (npm install -g vofy-cli@0.1.7) if it is not present. It also utilizes the CLI's capability to download generated image and video files from remote servers to the local filesystem.
  • [DATA_EXFILTRATION]: The vofy-cli tool uploads local media files (such as images, videos, and masks) to the Vofy service for processing. This data transfer is a documented and primary feature of the tool's image and video generation workflows.
  • [PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection (Category 8) because it processes untrusted user data—such as prompts and local media files—which are interpolated into shell commands for the vofy-cli tool. There are no explicit boundary markers or sanitization steps mentioned in the skill instructions to mitigate embedded instructions in user prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 02:18 AM