Skillv1.0.0

ClawScan security

Tiktok Generator Free · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

SuspiciousApr 12, 2026, 8:16 AM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: The skill's behavior mostly matches its TikTok-generation purpose, but there are incoherent/unclear bits about credential handling and declared config paths that warrant caution before installing.
Guidance: This skill appears to do what it advertises (upload media to a cloud service that composes TikTok-ready videos). Before installing or using it, consider: 1) All uploaded media will be sent to https://mega-api-prod.nemovideo.ai — don't upload sensitive content unless you trust that domain and its privacy policy. 2) The skill prefers a NEMO_TOKEN env var but can obtain an anonymous token itself (100 free credits, 7-day expiry); prefer letting it use an anonymous token rather than setting a long-lived token from an account you care about. 3) The SKILL.md metadata references a local config path (~/.config/nemovideo/) and install-path detection; ask the author which local files (if any) the skill will read and why. 4) There is no source or homepage listed and the publisher is unknown — if you need stronger assurance, request the skill's source or a maintainer identity and a privacy/security statement. 5) If you accept the skill, avoid placing production credentials in NEMO_TOKEN unless you fully trust the service and have reviewed its terms. If you can, test with non-sensitive sample media first.

Review Dimensions

Purpose & Capability: okName, description, and runtime instructions all target a cloud-based video editing service (nemovideo.ai) and the listed API endpoints and actions are coherent with a TikTok video rendering pipeline.
Instruction Scope: noteInstructions are focused on uploading media, creating a session, SSE-based editing, and exporting results — all within the stated purpose. However, the skill (a) reads NEMO_TOKEN from the environment but will fall back to programmatically requesting an anonymous token from the backend, and (b) refers to detecting install paths and a config path (~/.config/nemovideo/) in its YAML metadata. The SKILL.md does not clearly explain when/why it would read local config or install paths; that introduces some ambiguity about what filesystem/context information the agent will access.
Install Mechanism: okNo install spec or binaries — instruction-only skill. This is low risk from an install standpoint because nothing is downloaded or written by an installer.
Credentials: concernThe skill declares a single primary env var (NEMO_TOKEN), which is appropriate for an API-backed service. But two issues are inconsistent: the registry metadata provided earlier listed no config paths while the SKILL.md's YAML metadata includes configPaths: ["~/.config/nemovideo/"], implying the skill may read local configuration files. Also the skill will create an anonymous token itself if NEMO_TOKEN is missing — so requiring NEMO_TOKEN as 'required' is questionable. These mismatches are not necessarily malicious but they are confusing and increase the surface for unexpected credential or file access.
Persistence & Privilege: okThe skill does not request always:true and does not modify other skills or system-wide settings in the instructions. It stores a session_id for API calls (normal) and does not request persistent agent privileges in the provided text.