IMA AI Music Generator — Suno, DouBao
PassAudited by ClawScan on May 1, 2026.
Overview
This appears to be a disclosed music-generation integration, but users should review its IMA API key use, credit consumption, and some inconsistent marketing/version metadata before installing.
Install only if you trust IMA/imastudio.com with your prompts and API key. Expect the skill to create music-generation tasks through api.imastudio.com and potentially spend IMA credits. The artifacts mostly support music generation, despite some voiceover/narration marketing text.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The skill can authenticate to IMA as you and create generation tasks under your account.
The skill requires an IMA API key and uses it as a bearer token for the provider API. This is expected for the integration, but it is still account-level credential use.
`IMA_API_KEY` | `api.imastudio.com` | Open API auth (`Authorization: Bearer ...`)
Use a dedicated or revocable IMA API key if possible, and monitor credit/API usage.
Running the skill may spend IMA credits to generate music.
The skill creates provider-side generation tasks and explicitly notes that credits may be consumed. This is central to music generation, but users should be aware of cost-bearing actions.
`POST /open/v1/tasks/create` → get `task_id` ... Pre-generation: "🎵 开始生成音乐… 模型：[Name]，预计[X~Y]秒，消耗[N]积分"
Confirm the model, prompt, and expected credit cost before generating, especially if credits are paid or limited.
It may be harder to verify exactly which publisher/version you are installing.
The packaged metadata does not match the registry metadata shown for this review, which lists a different owner ID and version. This is a provenance/packaging consistency issue, not evidence of hidden code behavior.
"ownerid": "kn70cjr952qdec1nx70zs6wefn7ynq2t" ... "version": "1.2.2"
Prefer installing only if the registry owner, version, and homepage are trusted and consistent with the publisher you expect.
A user might expect voiceover/narration generation when the artifacts primarily support text-to-music generation.
The user-facing description mentions voiceovers and narration, while the documented fixed task type and model tables are for music generation. This mismatch could confuse users about the skill's real capability.
description: Generate voiceovers, narration, and spoken audio ... Task type: `text_to_music` (fixed)
Treat this as a music-generation skill and verify that the selected model matches the audio output you want.