ai-podcast-creation

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses a restricted execution profile in its configuration, limiting the Bash tool to only run commands starting with belt. This effectively prevents arbitrary command execution.
  • [EXTERNAL_DOWNLOADS]: The skill references installation procedures and resources from inference.sh and github.com/inference-sh. These are the official domains and repositories for the platform the skill is designed to interface with, representing normal functional dependencies.
  • [DATA_EXFILTRATION]: Analysis of the provided workflows shows that network operations are confined to the intended API endpoints of the service provider. There is no evidence of sensitive file access or unauthorized data transmission.
  • [PROMPT_INJECTION]: The skill includes instructions for the AI to process user documents and generate scripts. These are standard task-oriented instructions and do not attempt to bypass safety filters or override agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 08:29 PM
Security Audit — agent-trust-hub — ai-podcast-creation