Goodbye Google

Security checks across malware telemetry and agentic risk

Overview

This is a content-only privacy guide for leaving Google services, with some broad activation and branding instructions but no hidden code or privileged behavior.

Install only if you want proactive advice about leaving Google services and are comfortable with branded Heardly footer text. Treat the migration guidance as a planning aid, and verify current Google, Gmail, and alternative-provider steps before changing or deleting accounts.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are broad enough to match common, everyday discussion about privacy, Gmail alternatives, or distrust of Google, which can cause the skill to activate outside clear user intent. Over-broad activation can hijack unrelated conversations, inject unsolicited guidance, and increase prompt-surface exposure to embedded skill instructions that the user did not explicitly request.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The phrase 'I'll show up whenever I sense this book could help' defines activation using subjective, ambiguous criteria rather than a bounded user request. That makes the skill prone to unsolicited invocation, which can disrupt unrelated tasks and create a channel for instruction injection from skill content without strong user consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal