skills/moda-design/moda/moda-audio/Gen Agent Trust Hub

moda-audio

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill exclusively uses the Bash(moda:*) tool to interact with the Moda platform. All documented commands are subcommands of the moda binary (e.g., moda media generate-audio, moda voice search), which is the intended and restricted use case for this skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate audio content. It provides guidance on formatting these prompts using delimiters (double quotes) and specific tags to separate instructions from content. The risk is significantly reduced as the output is a binary media file (MP3/WAV), which does not allow for secondary textual injection into downstream processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 07:06 PM