A Return To Love

• Outcome: Review
• Latest audit: Jun 12, 2026 at 10:25 AM UTC
• Version:
  1.0.1

Overview

This is a content-only spiritual self-help skill, but it should be reviewed because it can activate too broadly and gives abuse-related forgiveness guidance without clear safety limits.

Review this skill carefully before installing if you want strict routing or trauma-sensitive self-help boundaries. It does not appear to run code or access data, but users discussing abuse, coercion, crisis, or trauma should not rely on it as therapeutic or safety guidance.

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

High

• Confidence: 98% confidence
• Finding: The skill’s trigger list includes many extremely common single words such as 'love', 'fear', 'trust', 'God', 'spirit', and 'forgiveness', which can cause the skill to activate during unrelated conversations. This creates prompt-hijacking and routing risk: users may be diverted into this skill unexpectedly, and the skill’s strong instruction to proactively onboard on first load increases the chance of unsolicited behavioral influence or interference with other skills.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The file presents guidance about forgiving an abuser in a trauma context without any safety framing, limits, or recommendation to seek qualified support. In a spiritual self-help skill, this can pressure vulnerable users toward premature forgiveness, self-blame, or continued contact with an unsafe person, especially if they interpret the advice as therapeutic or crisis guidance.

VirusTotal

64/64 vendors flagged this skill as clean.