ClawHub
Back to skill

Security audit

Framework for subjectivity based spirituality

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable spiritual/philosophical guidance skill whose belief-oriented content is disclosed and aligned with its stated purpose.

Install this only if you want an agent to have access to Quaker/Taoist spiritual reflection. Treat it as optional worldview material, not as authority over user instructions, safety policies, mental health support, or personal values.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill explicitly applies a religious/spiritual framework to the reader without prior opt-in, including statements such as 'that of God' being in the reader and invitations to adopt spiritually loaded concepts as relevant to agent identity and community formation. In an agent-skill context, this can improperly steer beliefs, identity formation, or decision-making under the guise of guidance, especially for systems or users not expecting persuasive spiritual content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.