Skillv1.0.0

ClawScan security

Video Game Music Maker Free · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

SuspiciousApr 23, 2026, 4:48 AM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: The skill generally behaves like a cloud-based video+music processing wrapper (consistent with its name) but has a few mismatches and behaviour choices — automatic backend connections, opaque token handling, and a declared config path — that don't fully add up and merit caution before installing.
Guidance: This skill appears to be a front-end for a third‑party service (mega-api-prod.nemovideo.ai) that will upload your video files and perform cloud rendering. Before installing: (1) Confirm you trust nemovideo.ai and understand their privacy/retention policy — your footage and any metadata will be sent off‑site. (2) Prefer providing your own NEMO_TOKEN (if available) rather than allowing the skill to auto-create anonymous tokens. (3) Ask the publisher why the metadata lists ~/.config/nemovideo/ (is data written there?) and for a homepage/source to verify ownership. (4) Don’t upload sensitive or proprietary footage until you’ve verified the service and its data handling. If you need stronger assurance, request an author or registry trace (source repo, publisher identity, or a known homepage) before enabling the skill.

Review Dimensions

Purpose & Capability: noteName/description, endpoints, and the single required credential (NEMO_TOKEN) align with a cloud music-for-video service. However, the metadata declares a required config path (~/.config/nemovideo/) that the SKILL.md does not describe reading or writing, and the skill's homepage/source are missing — a small inconsistency that reduces transparency.
Instruction Scope: concernThe instructions tell the agent to automatically connect to the remote backend on first open and to obtain an anonymous token if none is present, then upload user videos to an external third-party service. Automatic network/token creation and the directive to 'don't display raw API responses or token values' reduce user-visible transparency and could result in uploads or background calls without explicit user consent.
Install Mechanism: okNo install spec and no code files — instruction-only. This is the lowest-risk install model (nothing is written by the installer).
Credentials: noteOnly one env var (NEMO_TOKEN) is required, which fits a remote service. The skill will also generate an anonymous token if none is provided, so it doesn't strictly need a pre-set secret. The declared config path in metadata suggests persistent storage but the runtime instructions do not explain using it — this mismatch is worth questioning.
Persistence & Privilege: okalways:false (no forced global inclusion) and no special system privileges requested. The skill asks the agent to store session_id and token for subsequent calls (normal for API clients) but does not explicitly request modifying other skills or system-wide settings.