Back to skill
Skillv0.1.0
ClawScan security
Elevenlabs Pro · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
SuspiciousFeb 27, 2026, 1:38 AM
- Verdict
- suspicious
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's code and documentation require an ElevenLabs API key and perform expected TTS calls, but the registry metadata does not declare the required credential — this mismatch and the unknown source mean you should proceed cautiously.
- Guidance
- This skill does what it says (calls ElevenLabs API and writes audio files), but the registry metadata omits the required ELEVENLABS_API_KEY credential even though both SKILL.md and the included Python script require it. Because the package source is 'unknown', verify the origin before installing. If you install: (1) only provide a minimal-scope ElevenLabs API key (rotate it if compromised), (2) run the script in an isolated environment or container, (3) inspect the included scripts yourself (you already have them) and confirm network calls go only to api.elevenlabs.io, and (4) avoid pasting high-privilege credentials into third-party skills from unknown publishers. If you need higher assurance, ask the publisher to declare the required env var in the registry and provide a trusted homepage or source repository.
Review Dimensions
- Purpose & Capability
- noteThe SKILL.md and scripts/elevenlabs.py implement ElevenLabs TTS, voice listing, and credit checks and call https://api.elevenlabs.io/v1 — this matches the skill name/description.
- Instruction Scope
- okRuntime instructions limit actions to using the ElevenLabs API, listing voices, generating audio files, and querying subscription/credits. The instructions do not request unrelated files, system credentials, or external endpoints beyond api.elevenlabs.io.
- Install Mechanism
- okNo install spec is provided (instruction + code only). There are no downloads or archive extraction steps; risk from the install mechanism is low.
- Credentials
- concernThe SKILL.md and scripts require an ELEVENLABS_API_KEY (or --api-key) but the registry metadata lists no required environment variables or primary credential. That mismatch is an incoherence: the skill will fail without the API key and the registry did not declare it as a required credential. No other unrelated secrets are requested.
- Persistence & Privilege
- okThe skill is not always-enabled and does not request elevated agent/system persistence. It does write MP3 output to the filesystem (user-specified path), which is appropriate for its purpose.