ClawHub
Back to skill

Security audit

Test

Security checks across malware telemetry and agentic risk

Overview

This is a playful Tarot-style decision aid with broad activation language, but no evidence of hidden data access, persistence, credential use, or harmful behavior.

Install only if you want a casual randomized decision aid. Prefer explicit use for low-stakes tie-breaking, and do not rely on it for security, data integrity, production deployments, financial, legal, medical, or other consequential decisions.

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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation criteria are intentionally broad and include common phrases like 'whatever you think', 'surprise me', and generic ambiguity triggers. This can cause the skill to activate in many ordinary contexts and substitute randomized tarot-driven guidance where deterministic reasoning or clarification would be safer, reducing predictability and user intent alignment.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The 'When to Use' section permits activation on vague or ambiguous prompts without defining thresholds, exclusions, or examples of when clarification is required instead. In practice, this ambiguity increases the chance the skill is invoked for routine requests, leading to inconsistent behavior and possible misuse of randomness in contexts the user did not intend.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal