Skillv1.0.0

ClawScan security

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

Scanner verdict

BenignApr 18, 2026, 5:05 AM

Verdict: benign
Confidence: medium
Model: gpt-5-mini
Summary: The skill is internally consistent with its stated purpose (uploading videos to a NemoVideo backend to remove intros) and only needs a single API token, but there are a few minor inconsistencies and privacy/operational details you should verify before use.
Guidance: This skill appears coherent for cloud-based intro removal and only needs a single API token (NEMO_TOKEN). Before installing: confirm the API domain (mega-api-prod.nemovideo.ai) is a trusted endpoint for you; ask the publisher how uploaded videos are stored, how long they are retained, and whether exports or thumbnails persist on the backend; verify what the NEMO_TOKEN scope allows and where tokens/config files (e.g., ~/.config/nemovideo/) are stored or written; be aware the skill directs the agent to hide technical details from chat (less transparency). If you need stronger assurance, ask the publisher to provide a privacy/retention policy and clarify the configPaths discrepancy in the metadata.

Review Dimensions

Purpose & Capability: noteName/description (remove intros from videos) match the runtime instructions: create a session, upload video, request export and download URL. Requiring a NEMO_TOKEN for the remote API is proportionate. Minor inconsistency: the skill frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata showed no required config paths.
Instruction Scope: noteInstructions stay within the video-editing domain (session creation, SSE chat, upload, export polling). One UX instruction stands out: 'Keep the technical details out of the chat' — this asks the agent to hide technical actions from users, which is a non-security threat by itself but reduces transparency. The skill does not instruct reading unrelated files or environment variables beyond NEMO_TOKEN (aside from the optional config path in frontmatter).
Install Mechanism: okNo install spec or code files are present (instruction-only), so nothing is written to disk by the skill itself. This is a low-risk install posture.
Credentials: noteOnly a single credential (NEMO_TOKEN) is requested, which is appropriate for an API-backed editor. The frontmatter also lists a config path (~/.config/nemovideo/) not reflected in the registry metadata — clarify whether the skill will read or write that config directory. The skill describes a fallback anonymous-token flow (POST to /api/auth/anonymous-token) which is reasonable but means the agent will perform network calls to acquire/use tokens.
Persistence & Privilege: okThe skill is not always-enabled and does not request elevated platform privileges. It does not attempt to modify other skills or system-wide settings. Autonomous invocation is allowed (platform default) but not combined with other concerning privileges.