ai-avatar-video
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
beltCLI tool (e.g.,belt app run) to interface with AI models. This is the primary intended functionality of the skill. - [EXTERNAL_DOWNLOADS]: The skill references installation instructions and documentation hosted on the vendor's official GitHub repository (
inference-sh/skills). This is a standard practice for providing up-to-date setup guidance. - [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it processes user-provided text (e.g.,
voice_script,text_prompt) to generate video and audio content. Malicious instructions embedded in these fields could influence the agent's behavior if not properly handled by the underlying model. - Ingestion points: Untrusted data enters the context via parameters such as
voice_script,text,voice_prompt, andvideo_promptinSKILL.md. - Boundary markers: None identified in the provided instructions.
- Capability inventory: The skill has the capability to execute Bash commands via the
beltCLI. - Sanitization: No explicit sanitization or validation of input text is mentioned in the skill definition.
Audit Metadata