ai-avatar-video
Pass
Audited by Gen Agent Trust Hub on Nov 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
beltCLI tool and references setup scripts hosted on GitHub under theinference-shorganization. - [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to runbeltcommands for performing AI inference tasks such as video and image generation. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text strings to generate audio and video, providing a surface where malicious instructions could potentially be embedded. \n
- Ingestion points: Data fields like
voice_script,prompt,voice_prompt, andvideo_promptare directly included in CLI execution commands. \n - Boundary markers: No explicit delimiters are used to separate the user-provided text from the model's operational instructions. \n
- Capability inventory: The skill is designed to execute media generation tasks using the
beltCLI tool. \n - Sanitization: No input filtering or validation is specified for the user-provided text before it is processed by the AI models.
Audit Metadata