explainer-video-guide
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
beltCLI tool vianpx skills add belt-sh/cliand references setup documentation located athttps://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates a surface for indirect prompt injection by taking user-controlled input for media generation and passing it directly to CLI-based AI models.
- Ingestion points: User-provided text for video scene descriptions and voiceover scripts used in
belt app runcommands. - Boundary markers: The instructions do not employ specific boundary markers or delimiters to isolate user input from the rest of the prompt structure.
- Capability inventory: The skill utilizes the
beltCLI tool viaBashto invoke various AI models for video, image, and audio generation. - Sanitization: There is no evidence of input validation or sanitization for the user-provided strings before they are processed by the underlying models.
Audit Metadata