ai-podcast-creation

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, exfiltration attempts, or unauthorized command executions were detected. The skill's primary purpose is to provide documentation and examples for using audio generation tools.
  • [EXTERNAL_DOWNLOADS]: The skill references the official 'belt' CLI and associated skills for audio processing. It points to legitimate documentation on GitHub (inference-sh/skills) for installation instructions.
  • [COMMAND_EXECUTION]: The skill uses the 'belt' command to interface with specific AI models. These commands are well-scoped to the stated purpose of podcast creation and audio editing.
  • [PROMPT_INJECTION]: The skill includes templates for using LLMs (Claude) to generate podcast scripts from user-provided documents. While this creates a standard surface for indirect prompt injection (as the LLM processes external document content), it is a core feature of the intended workflow and does not contain malicious instructions or safety bypasses.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:26 PM
Security Audit — agent-trust-hub — ai-podcast-creation