tv-launcher-prototype

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  1.0.1

Overview

This is an instruction-only skill for generating Smart TV-style frontend prototypes, with no evidence of sensitive access, hidden execution, or persistence.

Install this if you want help creating TV or big-screen interface prototypes. Expect it to activate on TV, launcher, OTT, remote-control, or 10-foot UI requests; if you prefer a non-Chinese response, state your language preference when using it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger conditions are excessively broad and include generic phrases like requests to design a TV page or launcher, which can cause the skill to activate when a user did not explicitly intend to invoke it. In an agent setting, overbroad routing can override more appropriate skills, increase prompt-surface exposure, and cause unintended behavior or content generation outside the user's actual request.

Natural-Language Policy Violations

Medium

• Confidence: 88% confidence
• Finding: The skill metadata and instructions are written to produce Chinese-language behavior without indicating that output should follow the user's preferred language. This can cause mismatched responses, reduce transparency, and make it harder for users or downstream systems to validate generated content safely and accurately.

VirusTotal

66/66 vendors flagged this skill as clean.