Inner Excellence: Train Your Mind for Extraordinary Performance and the Best Possible Life

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 7:58 AM UTC
• Version:
  1.0.0

Overview

This is a self-help and performance-coaching skill with no executable code, credentials, or system access, though its activation language and spiritual framing may feel intrusive to some users.

Install this if you want Inner Excellence-style performance coaching and are comfortable with Samurai, sports psychology, and Christian/spiritual framing. Be aware it may trigger on broad mindset or performance phrases and appends Heardly branding to responses.

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 (3)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list is excessively broad and includes many generic terms such as common emotions, performance topics, and loosely related names/concepts. This can cause the skill to activate in unrelated conversations, overriding user intent and injecting unsolicited guidance, which is a prompt-scope and routing safety issue even without code execution.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The condition to trigger when a user 'just installed this skill or doesn't know how to start' is ambiguous and paired with a mandate to proactively present content without waiting. That creates a risk of unsolicited behavior and context hijacking, where the skill may interrupt normal interaction flow or activate based on weak signals unrelated to an actual request for this content.

Natural-Language Policy Violations

Medium

• Confidence: 88% confidence
• Finding: The file explicitly instructs the assistant to channel a voice rooted in Christian faith and to explain the 'heart' behind techniques, which can steer responses into a religious/spiritual framing without first confirming the user's preferences. In a mental-performance and self-help context, this can alienate users, create undue influence during emotionally vulnerable conversations, and cause the assistant to present belief-laden guidance as the default rather than an optional framing.

VirusTotal

58/58 vendors flagged this skill as clean.