Skills
Navigate
skills/halt-catch-fire/mutiny/image-to-video/Gen Agent Trust Hub

image-to-video

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the belt CLI via npx skills add belt-sh/cli and references external resources from the inference-sh and belt-sh GitHub organizations for installation and additional capabilities.
  • [COMMAND_EXECUTION]: The instructions rely on the belt command-line tool to perform remote inference, including user-authenticated actions like belt login and execution of various AI models via belt app run.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines templates that interpolate user-supplied prompts into JSON payloads processed by the belt tool. This presents a vulnerability surface where malicious input could influence the behavior of the underlying AI models.
  • Ingestion points: Prompt and image path fields in the belt app run command examples within SKILL.md.
  • Boundary markers: None provided in the command templates.
  • Capability inventory: The skill facilitates remote execution of AI inference models and handles local file paths for images.
  • Sanitization: No validation or escaping of the user-provided prompt strings is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — image-to-video