Skills
skills/qu-skills/skills/talking-head-production/Gen Agent Trust Hub

talking-head-production

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the belt-sh/cli tool from the npm registry and references setup documentation hosted on the inference-sh GitHub repository.
  • [COMMAND_EXECUTION]: Employs the belt CLI to perform authentication and execute remote AI applications for image, audio, and video processing.
  • [PROMPT_INJECTION]: The skill processes natural language input for video scripts and generation prompts, which constitutes a surface for indirect prompt injection.
  • Ingestion points: Processes user-provided strings through the voice_script, prompt, voice_prompt, and video_prompt fields in SKILL.md.
  • Boundary markers: Not utilized in the provided command-line examples.
  • Capability inventory: The skill enables remote media generation and application execution via the belt app run command.
  • Sanitization: No explicit input sanitization or validation is described for the processed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:26 PM
Security Audit — agent-trust-hub — talking-head-production