Social Media Ai Video Maker

Security checks across malware telemetry and agentic risk

Overview

This is a cloud video-generation skill whose external API, token, upload, editing, and export behavior matches its stated purpose, though users should understand it connects to nemovideo.ai and may send media there.

Install only if you are comfortable sending prompts, uploaded media, and generated video state to nemovideo.ai for cloud processing. Treat NEMO_TOKEN/session data as sensitive, and avoid using private, regulated, or confidential media unless you trust the provider’s handling and retention practices.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The routing table sends 'Everything else' to the SSE action, which creates an overly broad trigger surface for external API interaction. In practice, unrelated or ambiguous user prompts could be forwarded to the backend service unintentionally, causing unexpected data transmission or remote actions without sufficiently specific user intent.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill instructs automatic token acquisition and session creation on first interaction before doing anything else, without a clear user-facing consent step explaining that data and prompts will be sent to an external service. This is dangerous because it can silently authenticate and establish a remote processing context, increasing privacy and data-handling risk as soon as the skill is invoked.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal