talking-head-production
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
beltCLI tool for video production tasks. Theallowed-toolsconfigurationBash(belt *)effectively restricts the agent's shell execution capabilities to only this specific command, adhering to the principle of least privilege. - [EXTERNAL_DOWNLOADS]: The skill references installation documentation and resources hosted on the
inference-shGitHub repository. These references are essential for the operation of the described toolset and originate from the service provider's official infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where user-supplied text is used to generate video output, representing a standard injection surface.
- Ingestion points: Untrusted data enters the context via
voice_scriptandvoice_promptparameters inSKILL.md. - Boundary markers: The skill does not currently implement specific delimiters or instructions to ignore embedded commands within the input text.
- Capability inventory: The skill possesses command execution capabilities via
belt app runas documented inSKILL.md. - Sanitization: No explicit validation or escaping of the user-provided text is performed before being passed to the CLI tool.
Audit Metadata