ai-podcast-creation

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted document content by interpolating it into prompts for script generation and audio conversion.\n
  • Ingestion points: Document content and script text provided by the user are interpolated into prompts in SKILL.md (e.g., in the NotebookLM-Style Content section).\n
  • Boundary markers: The skill does not use specific delimiters or instructions to prevent the agent from obeying commands embedded within the input documents.\n
  • Capability inventory: Usage of the belt CLI tool via Bash to generate audio files and music segments.\n
  • Sanitization: There is no evidence of sanitization or validation for the external content before it is processed.\n- [EXTERNAL_DOWNLOADS]: The skill directs users to install the belt-sh/cli tool and references documentation hosted on the inference-sh GitHub repository. These resources are part of the vendor's ecosystem for this skill's functionality.\n- [COMMAND_EXECUTION]: The skill utilizes the belt CLI through bash commands to interact with AI services. Access is restricted to the belt command space in the environment configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:54 PM
Security Audit — agent-trust-hub — ai-podcast-creation