Skills
skills/inference-sh-9/skills/talking-head-production/Gen Agent Trust Hub

talking-head-production

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides a link to installation instructions hosted on the vendor's official GitHub repository.
  • [COMMAND_EXECUTION]: The skill provides several examples of shell commands using the vendor's CLI tool to interact with AI models.
  • [PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection as it processes user-provided text prompts for speech synthesis and image generation.
  • Ingestion points: User-provided text prompts in belt app run commands (e.g., in SKILL.md).
  • Boundary markers: None present in the provided examples.
  • Capability inventory: The skill uses the Bash(belt *) tool to execute model inference.
  • Sanitization: No explicit sanitization or validation of input prompts is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 05:15 PM
Security Audit — agent-trust-hub — talking-head-production