app-store-screenshots
Warn
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the
belt-sh/clipackage and references installation instructions from a remote GitHub repository (inference-sh/skills). These sources are external and not identified as trusted vendors. - [INDIRECT_PROMPT_INJECTION]: The skill provides templates for generating images and videos based on user-supplied prompts, which serves as an ingestion surface for potentially malicious instructions.
- Ingestion points: Prompts for
belt app runcommands inSKILL.md. - Boundary markers: Absent.
- Capability inventory: Shell command execution via the
beltCLI tool. - Sanitization: No input validation or filtering is provided for the interpolated prompt data.
- [COMMAND_EXECUTION]: The skill documentation relies on the execution of the
beltCLI tool to perform its core tasks, including authentication and invoking AI models.
Audit Metadata