Browser key (auto created by Firebase)

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:27 PM UTC
• Version:
  1.0.0

Overview

This is a simple greeting skill that only tells the agent how to respond to greetings, with no evidence of file access, credentials, persistence, or external actions.

This appears safe to install as a lightweight greeter. Be aware that its trigger wording is loose, so it may respond to casual greetings or mixed messages more often than expected; it does not show evidence of accessing files, credentials, accounts, or external services.

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

Medium

• Confidence: 88% confidence
• Finding: The trigger conditions are broad enough that the skill may activate during ordinary conversation rather than only on explicit greeting intents. This can cause unintended routing or response hijacking, though in this case the skill only returns a greeting and does not perform sensitive actions, which limits the security impact.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The activation guidance includes examples like general greetings and "what's up," but does not specify clear limits for mixed-intent messages. That ambiguity can cause the skill to trigger when the user is asking for something else, leading to misrouting or interruption of more appropriate skills.

VirusTotal

66/66 vendors flagged this skill as clean.