skills/voxflowstudio/skills/podcast/Gen Agent Trust Hub

podcast

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill extensively uses the voxflow command-line interface to generate podcast scripts and synthesize audio. Commands include voxflow podcast, voxflow login, and voxflow status.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the voxflow package from the official NPM registry as a prerequisite.
  • [PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection (Category 8) because it processes untrusted user-provided topics and potentially content from URLs to generate podcast dialogue.
  • Ingestion points: User-supplied topics via the --topic flag and potentially URLs mentioned in the description (SKILL.md).
  • Boundary markers: None explicitly defined in the provided commands to isolate the topic content from the generation logic.
  • Capability inventory: The skill executes shell commands (voxflow) and writes files to the local system (.wav, .json, .txt).
  • Sanitization: Not explicitly documented; the skill relies on the underlying LLM engine and voxflow CLI for content safety.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 11:49 PM
Security Audit — agent-trust-hub — podcast