Spiritual Midwifery

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only natural childbirth guidance skill with no malware indicators, but it should be reviewed because it gives high-stakes pregnancy and labor advice with broad activation and an under-balanced anti-intervention framing.

Review carefully before installing. This skill is not malicious software, but it may steer conversations about pregnancy, labor, birth, postpartum recovery, and breastfeeding toward natural/home-birth guidance. Use it only as educational book-based context, not as medical advice, and rely on a qualified clinician or midwife for pregnancy complications, labor decisions, C-section questions, pain management, bleeding, reduced fetal movement, fever, severe headache, high blood pressure, or any urgent symptoms.

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 (4)

Vague Triggers

High
Confidence
95% confidence
Finding
The trigger list is extremely broad and includes common pregnancy, birth, postpartum, and breastfeeding terms that appear in ordinary conversations. This can cause the skill to activate in contexts where the user did not request book-style guidance, increasing the chance of unsolicited, potentially unsafe childbirth recommendations in a sensitive health domain.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The statement that the skill will appear whenever it 'senses this book could help' creates an ambiguous activation rule with no clear safety boundary. In a maternal-health context, vague triggering can surface advice during high-risk or emergency discussions where contextual accuracy and professional escalation are critical.

Natural-Language Policy Violations

High
Confidence
98% confidence
Finding
The skill frames childbirth as 'normal, natural, and safe' and states that interference usually creates problems, which can bias users against medically necessary evaluation or intervention. Because the skill operates in pregnancy and labor contexts, this messaging may minimize danger signs, reinforce delayed care-seeking, and influence decisions about home birth or avoiding hospital care.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The file gives directive childbirth and postpartum guidance such as labor coping, late-pregnancy exercise, breastfeeding, and recovery advice without any disclaimer that it is informational rather than medical advice. In a health-related skill, users may rely on this guidance for real decisions during pregnancy or labor, which can be unsafe because appropriateness depends on individual risk factors, complications, and professional evaluation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal