Skillv1.0.0

ClawScan security

Ai Tool For Video Editing · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

SuspiciousApr 12, 2026, 5:34 PM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: The skill mostly aligns with a cloud video-editing service, but small inconsistencies around declared config paths and required credentials (and expectations about install-path detection) do not fully add up and warrant caution before installing.
Guidance: This skill appears to be a straightforward cloud video-editing frontend, but there are small mismatches you should clarify before installing: (1) Confirm why the manifest lists a config path (~/.config/nemovideo/) when the registry said none are required — will the skill read local config files? (2) The skill declares NEMO_TOKEN as required but also documents an anonymous-token flow; ask whether providing your own token gives elevated access vs anonymous tokens. (3) The skill will upload your raw video to https://mega-api-prod.nemovideo.ai — verify the service’s privacy policy and retention/deletion rules before uploading sensitive content. (4) Ask the publisher/source for provenance (the registry lists an opaque owner id and no homepage). If you proceed, test with non-sensitive, small videos first and avoid supplying unrelated credentials or secrets. If these questions are unanswered, treat the skill as higher risk and avoid installing it in sensitive environments.

Review Dimensions

Purpose & Capability: noteThe name/description match the instructions: the skill uploads video files and uses a remote API to render edits. Requesting a single service token (NEMO_TOKEN) is proportionate to a cloud rendering service. Minor mismatch: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) that the registry metadata said was not required.
Instruction Scope: noteRuntime instructions are focused on the remote API (session creation, SSE, uploads, exports) and on handling user-uploaded files — appropriate for an editing tool. Two points to note: (1) the skill instructs the agent to 'auto-detect' an install path to set X-Skill-Platform, which is odd for an instruction-only skill with no install spec; (2) the frontmatter mentions a config path although the SKILL.md does not clearly state when/if that path should be read. Both are scope-ambiguities worth clarifying.
Install Mechanism: okNo install spec and no code files — instruction-only. This is the lowest-risk install mechanism; nothing will be downloaded or written by an installer.
Credentials: concernThe skill declares a single primary credential (NEMO_TOKEN), which is reasonable for the described cloud API. However, the SKILL.md also documents an anonymous-token flow that generates a token if none is present, making the 'required' env var claim inconsistent. The frontmatter's config path raises the possibility of reading user config files; the registry earlier reported no required config paths. These inconsistencies about when/why environment or config access is needed are disproportionate to the stated purpose and should be clarified.
Persistence & Privilege: okThe skill is not marked always:true and does not request elevated/system-wide persistence. It relies on remote sessions and short-lived tokens; no privilege escalation or permanent presence is requested by the manifest.