Flow Ai Video

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This appears to be a coherent cloud video-editing skill, but using it sends chosen media and edit prompts to NemoVideo and relies on a Nemo token/session.

Before installing, be comfortable with sending chosen videos and editing instructions to NemoVideo's cloud service and with the skill using or creating a NemoVideo token. No local code execution or malicious behavior is evidenced in the provided artifacts.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

Using the skill can trigger cloud API calls, session creation, rendering, and polling without separate manual steps after the user invokes the workflow.

Why it was flagged

The skill directs the agent to initiate backend setup and API workflows automatically during use. This is expected for a cloud rendering integration, but users should know API actions can occur as part of normal operation.

Skill content
On first use, set up the connection automatically and let the user know ("Connecting...").
Recommendation

Use it only when you intend to send footage to the NemoVideo service, and review rendered outputs before publishing or sharing them.

#
ASI03: Identity and Privilege Abuse
Low
What this means

The token can authorize NemoVideo sessions, credits, uploads, and renders, so it should be treated as a service credential.

Why it was flagged

The skill uses a NemoVideo bearer token or obtains an anonymous one for the service. This credential use is disclosed and aligned with the cloud editing purpose.

Skill content
Look for `NEMO_TOKEN` in the environment. If found, skip to session creation. Otherwise: ... POST `https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token` ... Extract `data.token`
Recommendation

Keep NEMO_TOKEN private, use a dedicated token if possible, and revoke or rotate it if you no longer trust the integration.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

Any uploaded footage, URLs, edit prompts, and related session state may be processed by the external NemoVideo service.

Why it was flagged

The skill sends user-selected video files or URLs to the external NemoVideo backend for processing. This is central to the skill's purpose, but it is a sensitive data flow.

Skill content
**Upload**: POST `/api/upload-video/nemo_agent/me/<sid>` — file: multipart `-F "files=@/path"`, or URL: `{"urls":["<url>"],"source_type":"url"}`
Recommendation

Do not upload confidential, private, or regulated media unless you are comfortable with NemoVideo processing it under its service terms.