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

moda-audio

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text (scripts or descriptions) to generate audio content.
  • Ingestion points: User input is passed to the --prompt parameter of the moda media generate-audio command in SKILL.md.
  • Boundary markers: Instructions specify enclosing the user prompt in double quotes to delimit it from the command.
  • Capability inventory: The skill utilizes Bash(moda:*) for media operations and file management within the Moda ecosystem.
  • Sanitization: No specific data sanitization is performed by the skill itself; it relies on the platform CLI's internal handling of command-line arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 11:46 PM
Security Audit — agent-trust-hub — moda-audio