Back to skill
Skillv1.0.0
ClawScan security
SenseAudio Voice · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 13, 2026, 3:08 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only guide about SenseAudio voice selection, entitlements, and clone constraints and its requirements and instructions are internally consistent with that purpose.
- Guidance
- This is an informational, instruction-only skill about SenseAudio voice selection and cloning constraints and does not request credentials or install code, so its surface risk is low. Before installing, confirm you trust the skill author (source/homepage is unknown). Be aware that to actually check entitlements or query a voice list you or the agent will need the platform account context or API keys — those are not supplied by this skill. Also exercise normal caution around cloned-voice workflows (ensure you have proper consent, and verify any model names/plan tiers with the official SenseAudio docs). If the skill later adds explicit API calls, external endpoints, or requests keys, reevaluate for coherence and data-exfiltration risk.
Review Dimensions
- Purpose & Capability
- okThe name, description, and included docs all describe voice inventory, entitlement checks, and cloning constraints. The skill requires no binaries, env vars, or installs, which is appropriate for a purely informational guide.
- Instruction Scope
- noteThe SKILL.md stays within scope (confirm voice_id, check entitlement, ensure cloning completed, validate model/dictionary compatibility, provide fallbacks). It references querying the platform voice list endpoint but does not specify credentials or exact endpoints — this is reasonable for a generic guide but means the agent or user must supply account context or API keys at runtime.
- Install Mechanism
- okNo install spec or code files are present (instruction-only). That minimizes risk because nothing is written to disk or auto-installed.
- Credentials
- okThe skill does not request any environment variables, credentials, or config paths. If the user or agent needs to actually query a platform API to check entitlements, those credentials would be provided outside this skill, which is consistent with an informational/reference skill.
- Persistence & Privilege
- okThe skill is not marked always:true and has no install-time persistence. It does not request elevated privileges or modify other skills or system configs.