skills/magentosh/skills/ai-podcast/Gen Agent Trust Hub

ai-podcast

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents a complex multi-step pipeline for media generation using standard platform tools. It includes operational rules and best practices (e.g., sequential processing to avoid memory errors, framing guidelines) that are consistent with a benign, utility-focused skill.
  • [EXTERNAL_DOWNLOADS]: The skill references various external applications like pruna/p-image, phota/train, and inworld/text-to-speech-2. These appear to be official platform-integrated tools or well-known services (Google). The use of URLs for image and audio assets is necessary for the described media generation workflow and does not involve the execution of untrusted code.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to invoke platform-specific commands (infsh app run). This is used exclusively for triggering defined workflows in a managed environment and does not attempt to execute arbitrary or elevated shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 06:03 PM
Security Audit — agent-trust-hub — ai-podcast