voice-output

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill appears to perform its stated text-to-speech function, but it embeds an undeclared Doubao access token and sends spoken text to ByteDance’s TTS service.

Review this skill before installing. It likely does what it claims, but you should replace the bundled Doubao token with your own declared credential, understand that voice text is sent to ByteDance’s TTS API, and only use it on an environment where Python and macOS afplay are available.

Findings (3)

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.

What this means

Voice requests may run under a bundled provider account or token that the user cannot inspect, rotate, or scope through normal configuration; the token is also exposed to anyone with the skill files.

Why it was flagged

The script embeds a provider access token and uses it for Doubao API authorization, while the registry metadata declares no primary credential or required environment variable.

Skill content
APPID = "8982709936"
ACCESS_TOKEN = "gSlk...FNrbw"
...
"Authorization": f"Bearer; {ACCESS_TOKEN}"
Recommendation

Remove the hardcoded token, declare the required credential, load it from a secure user-controlled environment variable or config store, and document the minimum provider scope needed.

What this means

Anything included in a voice reply may be transmitted to the TTS provider for synthesis.

Why it was flagged

The text to be spoken is sent to ByteDance/Doubao’s TTS endpoint. This matches the skill’s stated purpose, but it is still an external data flow.

Skill content
url = "https://openspeech.bytedance.com/api/v1/tts"
...
"request": {
    "text": text,
    "text_type": "plain",
    "operation": "query"
}
Recommendation

Avoid using voice output for confidential content unless you are comfortable with that provider processing the text; the skill should document provider privacy and retention expectations.

What this means

Install-time checks may not warn users that this is macOS-oriented, requires local audio playback support, and depends on an external TTS credential.

Why it was flagged

The skill documentation lists runtime dependencies and provider credentials, but the supplied registry metadata says there are no required binaries, environment variables, primary credential, or install spec.

Skill content
## Dependencies

- Python3 (urllib, base64 built-in)
- afplay (macOS built-in)
- Doubao TTS credentials (APPID: 8982709936)
Recommendation

Declare required binaries, OS expectations, capability tags, and credential requirements in metadata so users can make an informed install decision.