p-video-avatar

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute belt CLI commands, which are used to interact with the Pruna P-Video-Avatar application for video generation and account management.
  • [EXTERNAL_DOWNLOADS]: The documentation references the installation of the belt-sh/cli Node.js package and points to configuration files hosted on the vendor's official GitHub organization (inference-sh). These are legitimate resources required for the skill's operation.
  • [PROMPT_INJECTION]: There is a potential for indirect prompt injection, as user-provided text for scripts and video prompts is interpolated directly into command-line arguments. 1. Ingestion points: SKILL.md template inputs for voice_script, video_prompt, and voice_prompt. 2. Boundary markers: The skill does not use specific delimiters to isolate user input in the CLI commands. 3. Capability inventory: The skill is scoped to execute the belt command via Bash. 4. Sanitization: No sanitization or escaping of the user-provided strings is performed within the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 04:03 PM
Security Audit — agent-trust-hub — p-video-avatar