Back to skill
Skillv1.0.0
ClawScan security
TTS文字转语音 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 7, 2026, 3:37 AM
- Verdict
- benign
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- This is an instruction-only TTS skill that consistently describes using a single public HTTP API to convert text to MP3 and does not request extra credentials or install components.
- Guidance
- This skill appears internally consistent and only needs network access to the listed endpoint. Before installing, consider: (1) the skill will send any text you provide to https://tts.wangwangit.com — do not submit sensitive data unless you trust that service; (2) verify the endpoint's reputation or request details from the skill author if you need an audit trail or data-retention policy; (3) test with non-sensitive text first to confirm behavior; and (4) if your organization requires vetted providers, prefer a known TTS service or a self-hosted solution instead.
Review Dimensions
- Purpose & Capability
- okName/description match the instructions: the SKILL.md shows how to POST text to a TTS endpoint and retrieve an MP3. No unrelated binaries, env vars, or config paths are requested.
- Instruction Scope
- noteInstructions are narrowly scoped to calling the specified HTTPS endpoint, saving the response to /tmp/tts_output.mp3, and sending it to the user. This is coherent for a TTS skill, but it will transmit the provided text to a third-party service (the endpoint tts.wangwangit.com), which may retain or log requests — consider privacy of any sensitive text.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill. Nothing is written to disk by an installer and no external packages are fetched by the skill itself.
- Credentials
- okNo environment variables, credentials, or config paths are requested. The SKILL.md explicitly states the API is free and requires no API key, which matches the registry metadata.
- Persistence & Privilege
- okSkill is not always-enabled, does not request elevated persistence, and contains no instructions to modify other skills or global agent configuration.