Tiktok Viral Slideshow

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:37 PM UTC
• Version:
  1.0.0

Overview

This skill appears to do what it says: it sends user-selected media to a named cloud service to create TikTok-style slideshow videos.

Install only if you are comfortable sending selected images, videos, URLs, prompts, and render metadata to the NemoVideo cloud backend. Avoid private, regulated, or sensitive media unless you trust that service's privacy and retention practices, and use explicit media-editing requests to avoid accidental activation.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Description-Behavior Mismatch

Medium

• Confidence: 82% confidence
• Finding: The undocumented URL-based upload path allows the skill to fetch remote user-supplied resources, expanding its trust boundary beyond local file uploads. That can enable server-side request abuse, unexpected third-party data transfer, or ingestion of hostile content from arbitrary URLs, especially when the capability is not clearly disclosed to users or reviewers.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The invocation guidance uses very generic language that could cause the skill to activate on ordinary conversation unrelated to explicit user intent. In an agent setting this can trigger unintended network calls, token creation, session creation, or media-processing actions without sufficiently clear consent.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The example trigger phrases are underspecified and overlap with common chat requests, increasing the chance of accidental routing into this skill. Because the skill can authenticate, create sessions, and interact with external APIs, accidental triggering has meaningful privacy and operational impact.

VirusTotal

61/61 vendors flagged this skill as clean.