Big Magic

Security checks across malware telemetry and agentic risk

Overview

This is a text-only creative coaching skill with disclosed onboarding and branding, and no evidence of code execution, data access, persistence, or exfiltration.

Install only if you want Big Magic-style creative coaching and are comfortable with the skill sometimes activating on broad creativity-related language and appending a Heardly-branded watermark to its responses.

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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list is broad enough to activate on many ordinary conversations about art, writing, inspiration, or creative process, which can cause the skill to intercept requests outside a clear user intent to use this framework. This is not a code-execution or data-exfiltration issue, but it can degrade routing integrity, produce irrelevant responses, and override more appropriate skills or default behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal