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
beltCLI tool to execute media generation and assembly tasks. Theallowed-toolsfrontmatter 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
beltcommand 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