← Back to Skills Marketplace
10951
Downloads
5
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install voice-wake-say
Description
Speak responses aloud on macOS using the built-in `say` command when user input indicates Voice Wake/voice recognition (for example, messages starting with "User talked via voice recognition on <device>").
Usage Guidance
Install this only if you want voice-recognition-triggered responses spoken aloud on a Mac. Be mindful that spoken responses may be overheard, and the `repeat prompt first` wording is unusual, but the reviewed artifacts do not show malicious or high-impact behavior.
Capability Analysis
Type: OpenClaw Skill
Name: voice-wake-say
Version: 1.0.1
The skill's primary function to use the local macOS `say` command for text-to-speech is benign, and the command execution (`printf '%s' "$SPOKEN_TEXT" | say`) is implemented safely. However, the `SKILL.md` file contains a critical instruction to the AI agent: "If the message instructs 'repeat prompt first', keep that behavior in the response." This instruction creates a significant prompt injection vulnerability, as it explicitly tells the agent to process and act upon arbitrary user-provided instructions embedded after the 'repeat prompt first' phrase, potentially allowing a malicious user to override the agent's intended behavior or security controls.
Capability Assessment
Purpose & Capability
The stated purpose is to speak assistant responses aloud when a Voice Wake-style message is detected, and the only runtime capability shown is the disclosed local macOS `say` command.
Instruction Scope
Instructions are mostly scoped to messages starting with `User talked via voice recognition`; the `repeat prompt first` line is awkward and could confuse agent behavior, but it does not instruct prompt disclosure, policy bypass, exfiltration, or unrelated actions.
Install Mechanism
The artifact is instruction-only with a single SKILL.md file; no executable scripts, package installs, setup hooks, or hidden install behavior are present.
Credentials
macOS `say` usage is proportionate to the skill purpose, local-only, and explicitly avoids cloud TTS providers.
Persistence & Privilege
No persistence, background workers, credential access, network access, elevated privileges, or account mutation authority are requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install voice-wake-say - After installation, invoke the skill by name or use
/voice-wake-say - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Remove device-specific trigger (make generic)
Metadata
Frequently Asked Questions
What is Voice Wake Say?
Speak responses aloud on macOS using the built-in `say` command when user input indicates Voice Wake/voice recognition (for example, messages starting with "User talked via voice recognition on <device>"). It is an AI Agent Skill for Claude Code / OpenClaw, with 10951 downloads so far.
How do I install Voice Wake Say?
Run "/install voice-wake-say" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Voice Wake Say free?
Yes, Voice Wake Say is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Voice Wake Say support?
Voice Wake Say is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Voice Wake Say?
It is built and maintained by xadenryan (@xadenryan); the current version is v1.0.1.
More Skills