Back to skill
Skillv1.0.0
ClawScan security
Shop Video · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
SuspiciousApr 23, 2026, 3:06 AM
- Verdict
- suspicious
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The skill's runtime instructions generally match its stated purpose (upload video → cloud render), but there are inconsistencies and privacy risks you should understand before installing.
- Guidance
- This skill appears to do what it says — it uploads your videos to a third-party render API and returns a processed MP4 — but pay attention to privacy and metadata mismatches before installing: - Confirm the service domain (mega-api-prod.nemovideo.ai) and the provider's reputation. There is no homepage or source listed in the registry metadata. - Understand that your video files (possibly containing sensitive product or customer information) will be uploaded to that external service. If in doubt, test with non-sensitive footage first. - The skill asks for a NEMO_TOKEN. If you don't already have one, the skill will create an anonymous token with 7‑day validity — consider using that rather than a long-lived production credential. - Ask the publisher why SKILL.md lists a local config path (~/.config/nemovideo/) while the registry metadata shows none. Accessing local config could expose other credentials; do not grant or place secrets there unless you trust the source. - If you will use the skill in sensitive environments, prefer creating minimal-scope/throwaway tokens, and do not allow the agent to access other credentials. If unsure, treat this skill as untrusted until you can confirm the vendor and the intended behavior.
Review Dimensions
- Purpose & Capability
- noteThe skill claims to convert product footage into shoppable videos and only requires a single service token (NEMO_TOKEN), which is coherent for a cloud rendering API. However, the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) while the registry metadata lists no required config paths — this inconsistency should be resolved because access to a local config directory would be out-of-scope for a simple upload/processing tool unless that directory holds credentials or client config.
- Instruction Scope
- noteInstructions are concrete and focused on interacting with a cloud API (anonymous-token creation, session start, file upload, SSE streaming, render/poll). That is within scope. The agent is explicitly instructed to upload user video files to https://mega-api-prod.nemovideo.ai and to persist session_id and use tokens; uploading user media to an external service is expected for this product but has privacy implications. The SKILL.md also requires including attribution headers and 'auto-detect' the platform from the install path, which implies the agent may inspect its environment/install path — this is reasonable but worth noting.
- Install Mechanism
- okNo install spec and no code files are present (instruction-only). This is the lowest-risk install pattern: nothing is written to disk by an installer from the registry.
- Credentials
- noteOnly one credential (NEMO_TOKEN) is declared as required and is appropriate for a cloud API. However, SKILL.md frontmatter mentions a config path (~/.config/nemovideo/) that would grant local config access if used; the registry metadata did not list that path — this mismatch is disproportionate and raises the question whether the agent will read local config files containing other secrets.
- Persistence & Privilege
- okalways:false and no special persistence is requested. The skill does not request to modify other skills or system-wide settings. The skill is allowed to be invoked autonomously by the model (default), which is normal; nothing in the skill amplifies this into a higher privilege.