p-video-avatar

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool to interact with the inference.sh platform. These commands (belt app run, belt login) are standard for using the documented service.
  • [EXTERNAL_DOWNLOADS]: The skill references a shell script installation link from a well-known source (GitHub) and documentation links from the official service domain (inference.sh). These references are informative and standard for technical documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided strings for voice_script and video_prompt. While these could theoretically contain injection attempts, they are processed by the remote AI model as data for video generation, and the skill provides a standard interface for this functionality with no immediate local risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:21 PM
Security Audit — agent-trust-hub — p-video-avatar