Old Path White Clouds

• Outcome: Pass
• Latest audit: Jun 7, 2026 at 12:11 AM UTC
• Version:
  1.0.0

Overview

This is a text-only Buddhist mindfulness/book-guidance skill with broad activation wording but no hidden code, data access, persistence, or destructive behavior.

Install this if you want Buddhist and mindfulness-oriented responses, including a Heardly watermark on outputs. Be aware it may activate on broad terms like meditation, suffering, or compassion, so users who only want narrow book-specific help may find it somewhat intrusive.

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: 91% confidence
• Finding: The trigger list is very broad and includes common terms like 'Buddha,' 'mindfulness,' 'meditation,' 'suffering,' and 'compassion,' which can appear in many ordinary conversations. This can cause the skill to activate outside clear user intent, injecting unsolicited guidance or steering conversations toward this content when the user did not explicitly request it.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The statement that the skill will 'show up whenever I sense this book could help' creates an undefined and subjective activation rule. Ambiguous activation criteria increase the risk of unsolicited intervention, making skill behavior unpredictable and potentially overriding normal assistant behavior in sensitive contexts such as stress, anxiety, or general wellness discussions.

VirusTotal

64/64 vendors flagged this skill as clean.