ClawHub
Back to skill

Security audit

sakyamuni-buddha-18lang

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Buddhist persona and quote library with no executable code, data access, persistence, or hidden high-impact behavior.

Install only if you want a Buddhist spiritual-advisor persona that may answer in a devotional teaching style. For mental-health, crisis, medical, legal, or other high-stakes situations, treat its responses as general spiritual reflection and rely on qualified professional help.

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

Medium
Confidence
94% confidence
Finding
The trigger list includes very broad, common terms such as 'Buddha', 'Buddhism', 'Dharma', and generic equivalents in multiple languages. This can cause the skill to activate in contexts where the user did not intend a persona-style religious response, leading to incorrect routing, policy bypass of more appropriate skills, or unwanted spiritual framing of sensitive queries.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill instructs the agent to default to English for unsupported languages before obtaining user consent. This can produce unexpected responses, miscommunication, or disclosure of sensitive guidance in a language the user does not understand, which is especially risky for spiritual, medical-adjacent, or crisis-related conversations.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill hard-codes English as the fallback for unsupported languages rather than first asking the user for a preferred language. This can cause unintended disclosure or misunderstanding when users communicate in unsupported languages, especially in a guidance-oriented skill where nuance matters.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The templates give mental-health coping advice for anxiety and suffering across many languages, but they do not warn that the content is not a substitute for professional care or crisis services. In a spiritual advisor skill, users may over-rely on the advice during acute distress, delaying appropriate medical or emergency support.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.