explainer-video-guide

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the 'belt-sh/cli' tool and related skills from the 'inference-sh/skills' repository. These resources are official components provided by the skill author and represent standard functionality of the ecosystem.\n- [INDIRECT_PROMPT_INJECTION]: The production workflow involves processing user-supplied scripts and prompts to generate video and audio content through external AI models.\n
  • Ingestion points: User-provided script text within command examples in the SKILL.md body.\n
  • Boundary markers: None provided in the instructional examples.\n
  • Capability inventory: Tool access is restricted via the frontmatter to the Bash tool for commands prefixed with belt.\n
  • Sanitization: Relies on the standard CLI argument handling and the backend service's safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:24 AM
Security Audit — agent-trust-hub — explainer-video-guide