← Back to Skills Marketplace
264
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install vwu-tts
Description
调用 vwu.ai 语音合成模型speech-2.8-hd和speech-2.8-turbo,需配置API key并支持OpenAI兼容接口。
Usage Guidance
Before installing: (1) confirm the registry metadata is corrected to list VWU_API_KEY as a required credential. (2) Ensure curl and jq are available on the agent runtime or adjust the script; SKILL.md should mention these prerequisites. (3) Be cautious about VWU_BASE_URL — it can redirect requests to any host if you or an attacker sets that env var; don't set it unless you trust the host. (4) Note the script prints the first 8 characters of your API key on quota errors — consider rotating keys if you expose logs to others. (5) The SKILL.md usage example and the script's argument parsing differ; test locally first. If any item is unclear, ask the publisher to clarify or provide a corrected SKILL.md and registry metadata before use.
Capability Analysis
Type: OpenClaw Skill
Name: vwu-tts
Version: 1.0.0
The script vwu-chat.sh contains a shell injection vulnerability because it expands the $PROMPT and $MODEL variables directly within a double-quoted string passed to curl without proper escaping or using jq to construct the JSON payload safely. This could allow an attacker to execute arbitrary commands or manipulate the API request. While the behavior aligns with the stated purpose of calling the vwu.ai API, the lack of input sanitization is a significant security flaw.
Capability Assessment
Purpose & Capability
Skill name/description (vwu.ai TTS models) align with the code and SKILL.md: the script calls vwu.ai chat completions for the two listed models. However, the registry metadata claims no required env vars or primary credential while the SKILL.md and the included script clearly require VWU_API_KEY — this mismatch is inconsistent and should be corrected.
Instruction Scope
SKILL.md instructs setting VWU_API_KEY and calling a CLI, which matches the script, but it omits mention of VWU_BASE_URL (the script allows overriding the endpoint). The script also assumes curl and jq are available (SKILL.md/registry do not declare binaries). The script prints a masked but partially-identifying prefix of the API key on quota errors, which is a small leakage. The SKILL.md example uses a --model flag but the script expects positional args, a usability/instruction mismatch.
Install Mechanism
No install spec (instruction-only with a small shell script). That is low risk because nothing is automatically downloaded or installed by the skill bundle itself.
Credentials
Only VWU_API_KEY is needed for operation, which is proportionate — but the registry metadata does not declare this required credential. Also the script exposes the first 8 characters of the key on certain errors and accepts VWU_BASE_URL (undocumented) which could be pointed at a non-official endpoint if an environment variable is set.
Persistence & Privilege
The skill does not request permanent presence (always:false) and does not modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install vwu-tts - After installation, invoke the skill by name or use
/vwu-tts - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - Complete vwu.ai model collection
Metadata
Frequently Asked Questions
What is vwu.ai TTS Models?
调用 vwu.ai 语音合成模型speech-2.8-hd和speech-2.8-turbo,需配置API key并支持OpenAI兼容接口。 It is an AI Agent Skill for Claude Code / OpenClaw, with 264 downloads so far.
How do I install vwu.ai TTS Models?
Run "/install vwu-tts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is vwu.ai TTS Models free?
Yes, vwu.ai TTS Models is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does vwu.ai TTS Models support?
vwu.ai TTS Models is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created vwu.ai TTS Models?
It is built and maintained by a3273283 (@a3273283); the current version is v1.0.0.
More Skills