Video Loop Ai

AdvisoryAudited by Static analysis on May 11, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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.

What this means

The agent can use the NemoVideo token or anonymous starter token to create sessions, upload media, check credits, and start exports.

Why it was flagged

The skill uses a provider bearer token for all backend requests. This is expected for the NemoVideo integration, but it gives the agent delegated access to the provider account/session and credits.

Skill content
Every API call needs `Authorization: Bearer <NEMO_TOKEN>`
Recommendation

Use only a token intended for this service, monitor credit usage, and avoid placing unrelated secrets in the NEMO_TOKEN environment variable.

What this means

Videos, images, or audio provided to the skill may leave the local/chat environment and be processed on NemoVideo cloud systems.

Why it was flagged

The workflow sends user-selected media files or URLs to the NemoVideo cloud API. This is central to the skill’s purpose, but it is still an external data transfer users should notice.

Skill content
`/api/upload-video/nemo_agent/me/<sid>` | POST | Upload a file (multipart) or URL.
Recommendation

Do not upload private, regulated, or confidential media unless you trust the provider and its retention/privacy terms.

What this means

When invoked, the agent may change the cloud editing session, start render jobs, and produce exports based on the user’s request.

Why it was flagged

The skill directs the agent to interact with a remote editing pipeline and perform edits/exports through API calls. This is coherent with the stated cloud video-editing purpose, but it is still an operational authority to mutate a cloud project session.

Skill content
| `/run_sse` | POST | Send a user message. Body includes `app_name`, `session_id`, `new_message`. Stream response with `Accept: text/event-stream`.
Recommendation

Review requested edits and exports before asking the agent to render or download final results, especially if credits or paid plans are involved.

What this means

Users have less independent context for verifying who operates or maintains the skill and backend service.

Why it was flagged

The registry context does not provide a source repository or homepage. There is no local code or install script in the supplied artifacts, so this is a provenance note rather than a security concern.

Skill content
Source: unknown; Homepage: none
Recommendation

Verify that `mega-api-prod.nemovideo.ai` is the service you intend to use before sending media or credentials.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

A render may continue or become hard to track if the session is interrupted.

Why it was flagged

The skill discloses that provider-side render jobs can outlive the immediate chat/tab state. This is expected for cloud rendering, but users should be aware of potential orphaned jobs or credit use.

Skill content
The session token carries render job IDs, so closing the tab before completion orphans the job.
Recommendation

Wait for renders to complete when possible and check credit/job status if a session is closed or interrupted.