Listen

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

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

Incorrect or sensitive correction entries could affect future transcriptions or reveal user-specific vocabulary if the skill file is shared.

Why it was flagged

The skill is designed to persist learned corrections and context, which is purpose-aligned but means user-specific names, terms, or correction patterns may be reused later.

Skill content
This skill auto-evolves. Track transcription errors and learn corrections.
Recommendation

Review the Corrections, Patterns, Context, and Never sections periodically and avoid storing confidential terms unless needed.

What this means

Changing STT settings may switch the provider used for future audio transcription, with possible privacy, accuracy, or cost effects.

Why it was flagged

The skill documents a configuration-changing gateway operation; this fits the stated STT setup purpose, but it can affect future transcription behavior.

Skill content
Use gateway config.patch to update STT settings.
Recommendation

Confirm the selected provider and settings before applying configuration patches.

What this means

A real API key could authorize use of the user's provider account and may incur usage or expose audio to that provider.

Why it was flagged

The skill includes examples for provider API keys, which is expected for Groq/OpenAI STT setup but still involves account credentials.

Skill content
groq:
  apiKey: "gsk_..."
...
openai:
  apiKey: "sk-..."
Recommendation

Use scoped provider keys where available, store them only in trusted configuration locations, and choose the local provider if offline privacy is required.