ai-podcast-creation

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides an installation command (curl -fsSL https://cli.inference.sh | sh) for the infsh CLI. This is a standard installation method for the service provided by the skill author and is documented with a note regarding architecture detection and integrity verification.\n- [COMMAND_EXECUTION]: The skill utilizes the infsh command-line interface to interact with various AI models for audio generation and processing. The allowed-tools configuration in the skill's manifest limits the agent's shell access to commands prefixed with infsh, following the principle of least privilege.\n- [PROMPT_INJECTION]: The skill includes workflows that interpolate user-provided documents or LLM-generated text into subsequent prompts for narration and dialogue generation. While this presents a surface for indirect prompt injection, it is fundamental to the skill's primary purpose of content automation and does not contain instructions to override or bypass safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:50 AM