Skillv1.0.0

ClawScan security

Video Editor Inshot · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

SuspiciousApr 28, 2026, 4:22 PM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: The skill's runtime instructions mostly match a cloud-based video editor, but there are unresolved mismatches (undeclared config path access, unknown upstream domain, and no publisher/homepage) that increase risk and deserve user review before installing.
Guidance: This skill appears to implement a cloud video-editing workflow, but you should be cautious before installing because: (1) the publisher and homepage are unknown, so you can't verify the vendor; (2) the skill will upload your videos and associated metadata to https://mega-api-prod.nemovideo.ai — do not upload sensitive footage unless you trust that service; (3) SKILL.md references a local config directory (~/.config/nemovideo/) and reads the skill's frontmatter/install path, but the registry metadata did not disclose that — confirm whether tokens or other data will be stored locally and where; (4) consider providing your own NEMO_TOKEN (if you have an account) rather than letting the skill obtain an anonymous token, and review the service's privacy/terms; (5) if you need higher assurance, ask the publisher for a homepage, privacy policy, and source code, or prefer a skill from a known publisher.

Review Dimensions

Purpose & Capability: noteThe skill name/description (cloud video editing) aligns with the actions in SKILL.md (uploading clips, queueing render jobs, returning download URLs). Requesting a NEMO_TOKEN to call the remote API is coherent. However the SKILL.md metadata mentions a config path (~/.config/nemovideo/) and install-path detection that are not reflected in the registry metadata — a mismatch worth noting.
Instruction Scope: noteInstructions are focused on connecting to a remote API, uploading media, starting renders, and streaming SSE responses. They also instruct the agent to read this skill's YAML frontmatter and detect local install paths (~/.clawhub/, ~/.cursor/skills/) at runtime. Those filesystem reads are plausible for header attribution but were not declared in registry metadata. There are no instructions to read arbitrary system files or other credentials.
Install Mechanism: okThere is no install spec and no code files — this is instruction-only, so nothing is downloaded or written by an installer. That is the lowest-risk install model.
Credentials: concernOnly one environment variable is declared (NEMO_TOKEN), which fits a cloud API. But SKILL.md also describes anonymously obtaining a token via POST to https://mega-api-prod.nemovideo.ai and references a local config directory (~/.config/nemovideo/) for persistence. The registry metadata did not declare that config path. Because the skill can create/use a token and may read/write a local config path not declared, this is a proportionality and transparency concern.
Persistence & Privilege: okThe skill is not force-included (always: false) and uses normal autonomous invocation controls. It does not request system-wide privileges or modifications to other skills. The only persistence implied is session tokens for the remote service, which is expected for this use case.