Skillv0.1.3

ClawScan security

Voice.ai: Creator Voiceover Forge · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

SuspiciousFeb 11, 2026, 9:44 AM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: The skill mostly does what it says (local script chunking + TTS calls to Voice.ai), but there are inconsistencies about required credentials and endpoints and the package/source trustworthiness is unclear — review before providing real API keys or running it.
Guidance: What to check before installing or running: - Confirm the API key requirement: SKILL.md and the code require VOICE_AI_API_KEY (or VOICEAI_API_KEY). The registry metadata incorrectly lists no required env vars — treat the SKILL.md/code as authoritative. - Do not paste a production VOICE_AI_API_KEY until you verify the service endpoint and publisher. The code points to https://dev.voice.ai and TROUBLESHOOTING warns that production endpoints may be placeholder; use --mock to test locally without sending data. - Verify the publisher/source: homepage is missing and owner id is an opaque string. README references a GitHub repo (gizmoGremlin) — inspect that upstream repo or contact the author to confirm authenticity before trusting real credentials. - Review bundled binary (voiceai-vo.cjs) or run in an isolated environment/container. Running with --mock first lets you exercise the pipeline without network calls. - Legal/privacy note: the voice catalog includes names that imply celebrity/character voices; ensure you’re comfortable with any potential voice-mimicry/licensing issues for your use case. If you want higher confidence: ask the publisher for a canonical homepage or GitHub link, verify the API base (production vs dev), and run the bundled CLI in --mock mode to validate local behavior before providing secrets.

Review Dimensions

Purpose & Capability: noteThe skill's name/description (voiceover pipeline using Voice.ai TTS) aligns with the code and instructions: it chunks scripts, calls a TTS API, stitches audio, and optionally muxes into video. Requesting a VOICE_AI_API_KEY is expected for this purpose. However, registry metadata at the top lists "Required env vars: none" and "Primary credential: none" while SKILL.md and the code require VOICE_AI_API_KEY; that mismatch is unexplained and reduces trust in the metadata.
Instruction Scope: okSKILL.md and the code instruct the agent to read a script file, optional templates in the skill directory, optional .env file, and (if requested) a local video file; the only network transmission described is sending script text to the Voice.ai API for TTS. Nothing in SKILL.md or the visible source asks the agent to read unrelated system files or exfiltrate other data.
Install Mechanism: okThere is no external install step; the package includes a bundled Node.js CLI (voiceai-vo.cjs). No downloads from arbitrary URLs or remote installers are present. The skill requires Node.js 20+ to run the bundled file; ffmpeg is optional and local. This is a low-risk install mechanism as delivered.
Credentials: concernFunctionality requires a single API key (VOICE_AI_API_KEY / alternate VOICEAI_API_KEY), which is proportionate. However, the public registry metadata claims no required env vars while SKILL.md and code declare and read VOICE_AI_API_KEY (and an alternate VOICEAI_API_KEY), creating an inconsistency. Also the skill references a base URL of https://dev.voice.ai (a dev/staging domain) and TROUBLESHOOTING warns that 'real API not yet configured' and suggests using --mock; that indicates the endpoints may be placeholders. Do not supply a production API key until you confirm the real endpoint and the publisher's identity.
Persistence & Privilege: okThe skill is not marked always:true and does not request system-wide privileges. It does not modify other skills or agent-wide settings in the files shown. It runs as a local Node process when invoked; normal for a CLI-style skill.