Trimmer High Quality
ReviewAudited by ClawScan on Apr 30, 2026.
Overview
This appears to be a cloud video-trimming skill, but it uploads your footage to NemoVideo and uses a service token/session to process and export clips.
Install or use this skill only if you are comfortable uploading the selected footage to NemoVideo's cloud service and using a NEMO_TOKEN or anonymous starter token. For private or sensitive videos, ask where data is sent and avoid starting exports you do not want processed.
Findings (9)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Backend responses may guide editing or export steps on the user's video session.
The skill instructs the agent to translate backend GUI-style messages into API actions. This is aligned with the remote editor workflow, but it means backend text can steer subsequent agent actions.
| "click [button]" / "点击" | Execute via API |
Use the skill for intended video-editing tasks and review requested uploads/exports if the outcome seems unexpected.
Your video files may be uploaded and rendered by the external service.
The skill uses remote API actions to upload files and start exports. These actions are central to cloud video trimming, but they can send user content and consume service credits.
Upload — `POST /api/upload-video/nemo_agent/me/<sid>` ... Export — `POST /api/render/proxy/lambda`
Only provide videos you are comfortable processing through the NemoVideo cloud service.
The skill acts under a NemoVideo token for session creation, upload, credit checks, and rendering.
The skill requires a NemoVideo bearer token, or creates an anonymous starter token if one is not present. This is expected for the provider integration and no credential leakage is shown.
Every API call needs `Authorization: Bearer <NEMO_TOKEN>`
Use a token intended for this service and avoid sharing broader credentials.
You have less publisher or homepage information to verify before trusting the cloud service integration.
The skill has limited provenance metadata. There is no install script or local code, so the main trust decision is whether the listed remote service is acceptable.
Source: unknown; Homepage: none
Confirm you trust the skill owner and the NemoVideo service before uploading private footage.
Your project state and media metadata may remain associated with the remote session while the job is active.
The workflow depends on a remote session that carries project state, media information, and render job identifiers. This is normal for a cloud editor but means context persists with the provider during the task.
The `session_id` in the response is needed for all following requests.
Avoid uploading sensitive footage unless you are comfortable with provider-side session storage and processing.
Prompts, editing instructions, and session context may be sent to and interpreted by the external backend.
The skill exchanges messages and internal tool-call signals with a remote SSE backend. The endpoint is fixed and authenticated, but users may not see all backend-driven internal actions.
Chat (SSE) — `POST /run_sse` with `session_id` and your message ... Tool calls stay internal.
Do not include sensitive information beyond what is necessary for the video edit, and verify outputs before using them.
An in-progress render may continue without an easy visible recovery path if the session is interrupted.
A render job can continue or become orphaned if the user leaves before completion. This is disclosed and tied to the rendering purpose, but it can affect job tracking or credits.
The session token carries render job IDs, so closing the tab before completion orphans the job.
Keep the session open until export completes when possible, especially for important or credit-consuming renders.
The chat may not explain token creation, API calls, or backend session details unless the user asks.
The skill tells the agent not to show technical details after connecting. The artifacts otherwise disclose the cloud API workflow, so this is a transparency note rather than evidence of deception.
Tell the user you're ready. Keep the technical details out of the chat.
Ask the agent to explain where files are uploaded and how the token/session is used if you need more transparency.
A cloud render may keep running even if you stop interacting before it completes.
The artifact discloses that a server-side render job may continue after the local interaction is interrupted. This is purpose-aligned rendering behavior, not self-propagation or hidden local persistence.
closing the tab before completion orphans the job
Avoid starting exports you do not want completed, and keep track of active render jobs.