explainer-video-guide

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to install the belt CLI and supplementary skills from external GitHub repositories. * Evidence: npx skills add belt-sh/cli in the quick start instructions. * Evidence: npx skills add inference-sh/skills@ai-video-generation. * Evidence: Installation instructions at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided prompts that are passed to shell commands, creating a potential injection surface. * Ingestion points: JSON input parameters in belt app run commands (e.g., scene descriptions and scripts). * Boundary markers: None. * Capability inventory: The skill is configured to use the Bash tool to run the belt CLI. * Sanitization: There is no evidence of input validation or sanitization for the user-provided prompt content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:21 PM
Security Audit — agent-trust-hub — explainer-video-guide