explainer-video-guide

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and external resources from the inference-sh repository on GitHub.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool to execute media generation and assembly tasks. The allowed-tools frontmatter property limits the shell capability to this specific tool, following the principle of least privilege.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves interpolating user-provided text into prompts for generative AI models, which is a potential surface for indirect injection attacks.
  • Ingestion points: Visual production prompts and voiceover script inputs within SKILL.md.
  • Boundary markers: No specific delimiters are used to wrap user-provided text in the command examples.
  • Capability inventory: The skill utilizes the belt command to interface with remote AI models and local media merging tools.
  • Sanitization: The instructions do not specify any validation or sanitization for the inputs before they are passed to the CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — explainer-video-guide