Voice Wake Say TTS Responses (Native)

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: clawdbot-skill-voice-wake-say Version: 0.1.0 The skill is designed to use the local macOS `say` command for text-to-speech under specific conditions. It explicitly avoids cloud-based TTS, which is a good security practice. The instructions for the agent are highly restrictive regarding when and what to speak, using the agent's processed final response as input to `say`. The command execution `printf '%s' "$SPOKEN_TEXT" | say` is a safe way to pass text to the `say` utility, preventing shell injection. There is no evidence of data exfiltration, malicious execution, persistence, or obfuscation. The minor prompt injection vector related to 'repeat prompt first' only influences the spoken output, not arbitrary command execution or data exfiltration, and is within the scope of the skill's intended function.

Findings (0)

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

When the trigger phrase is present, the assistant may speak its response aloud on the local Mac.

Why it was flagged

The skill instructs the agent to invoke a local shell command for text-to-speech. This is central to the stated purpose and uses piped text rather than interpolating it into executable arguments, so it is a disclosed, purpose-aligned command-use note rather than a concern.

Skill content
printf '%s' "$SPOKEN_TEXT" | say
Recommendation

Use this only where audible responses are appropriate, and avoid triggering it for sensitive content if others may hear the output.

What this means

Users on non-macOS systems may install a skill that cannot work as intended, and compatibility expectations are less clear.

Why it was flagged

The metadata does not declare the macOS dependency or required `say` binary, even though the skill description and instructions are macOS-specific. This is a packaging/disclosure mismatch, not evidence of hidden code.

Skill content
OS restriction: none; Required binaries (all must exist): none
Recommendation

Declare macOS as the supported OS and `say` as a required binary so users and platforms can understand compatibility before installation.