Body Kindness Transform Your Health From The Inside Out And Never Diet Again

• Outcome: Pass
• Latest audit: Jun 13, 2026 at 9:17 AM UTC
• Version:
  1.0.0

Overview

This is a static wellness guidance skill with disclosed behavior and no code execution, credentials, persistence, or data access, though users should treat its nutrition guidance as general advice.

Install only if you want anti-diet Body Kindness guidance. Treat food, tracking, and body-image advice as general wellness education, and follow clinician guidance for medical conditions, allergies, prescribed diets, diabetes, or eating-disorder concerns.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• 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

Findings (3)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger list is broad and includes common wellness phrases such as 'self-love,' 'body image,' and 'self-compassion,' which can appear in many unrelated conversations. This can cause the skill to activate when the user did not intend to invoke it, potentially overriding more relevant guidance or injecting unsolicited health content into sensitive discussions.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The instruction to trigger when a user says they just installed the skill or does not know how to start is ambiguous and mandates proactive output without a clear opt-in. That increases the chance of unsolicited activation and can lead the assistant to interrupt unrelated conversations or expose skill behavior based on weak contextual signals.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The content gives broad health-related guidance to stop tracking and to rely on unrestricted permission/intuitive cues without any qualification for users with diabetes, medically prescribed diets, allergies, or active/past eating disorders. In a wellness skill that may be used as actionable advice, omission of safety boundaries can mislead vulnerable users into abandoning clinically necessary monitoring or treatment-supportive structure.

VirusTotal

49/49 vendors flagged this skill as clean.