gen-ai-audio

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a comprehensive guide for audio generation tasks using the Picsart gen-ai ecosystem. It provides clear mappings between user intent (e.g., narration, music, sound effects) and the appropriate AI models.
  • [COMMAND_EXECUTION]: The instructions include shell command examples that use the gen-ai CLI in combination with standard tools like jq, curl, and ffmpeg. These examples are designed to automate the generation, retrieval, and basic processing of audio files, which is consistent with the skill's stated purpose.
  • [EXTERNAL_DOWNLOADS]: The skill demonstrates how to download generated audio content via curl based on URLs returned by the gen-ai tool. These operations are part of the standard workflow for interacting with the vendor's audio generation API.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided text for audio generation, it does so within the context of media production. There is no evidence of unsafe interpolation or surfaces where untrusted data could compromise the agent's execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 09:30 AM
Security Audit — agent-trust-hub — gen-ai-audio