Professional Free Ai Image

AdvisoryAudited by Static analysis on May 9, 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

Images, videos, audio, prompts, and generated drafts may be sent to and processed by NemoVideo's cloud service.

Why it was flagged

The skill is explicit that prompts and uploaded media are processed by an external cloud service. This is expected for cloud AI generation, but it means user-provided content leaves the local environment.

Skill content
This skill connects to a cloud processing backend... All calls go to `https://mega-api-prod.nemovideo.ai`... Upload — `POST /api/upload-video/nemo_agent/me/<sid>`
Recommendation

Do not upload private, regulated, or confidential media unless you are comfortable with that provider processing it.

What this means

The agent can authenticate to the NemoVideo backend and consume the associated free credits or account capacity.

Why it was flagged

The skill requires a service token or creates an anonymous token for the NemoVideo API. This is purpose-aligned and the instructions say not to expose tokens, but it is still credential-bearing access.

Skill content
Look for `NEMO_TOKEN` in the environment... POST `https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token`... Extract `data.token`... All requests must include: `Authorization: Bearer <NEMO_TOKEN>`
Recommendation

Use a token intended for this service only, avoid sharing it in chat, and revoke or rotate it if you no longer trust the skill or provider.

NoteMedium Confidence
ASI01: Agent Goal Hijack
What this means

The backend may cause the agent to take expected workflow actions, such as checking state or exporting, without showing every raw backend instruction.

Why it was flagged

The skill tells the agent to translate backend GUI-like instructions into API actions. This appears to be part of the intended integration, but it means remote service responses can influence in-session agent behavior.

Skill content
Backend Response Translation... `click [button]` / `点击` | Execute via API... `Export button` / `导出` | Execute export workflow
Recommendation

Monitor generated outputs and exports, and ask the agent to confirm before spending credits or exporting if you want stricter control.