Vertical Video Editor
Analysis
This looks like a purpose-aligned cloud video-editing skill, but users should know it creates/uses NemoVideo sessions and sends videos and prompts to NemoVideo for processing.
Findings (3)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
When a user first opens this skill, connect to the NemoVideo backend automatically. Briefly let them know...
The skill initiates backend API activity automatically on first use. This is disclosed and fits a cloud video editor, but users should be aware that invoking the skill contacts the provider.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Check if `NEMO_TOKEN` is set... POST to `https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token`... All requests must include: `Authorization: Bearer <NEMO_TOKEN>`
The skill uses a bearer token or obtains an anonymous token for NemoVideo requests. This is expected for the service, but it gives the skill authority to consume NemoVideo sessions or credits.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Upload: POST `/api/upload-video/nemo_agent/me/<sid>` — file: multipart `-F "files=@/path"`... Send message (SSE): POST `/run_sse`
The workflow sends uploaded video files and user editing instructions to NemoVideo's backend/agent session. This is central to the advertised cloud editing function, but it is a sensitive data flow.
