ClawHub
Back to skill

Security audit

WaitingForMacGuffin

Security checks across malware telemetry and agentic risk

Overview

This skill appears to provide Oscar prediction-market research and does not show evidence of hidden access, persistence, or harmful actions.

Install only if you want Oscar prediction-market research. Treat any betting picks as informational, verify current odds and local gambling rules yourself, and do not rely on the skill as financial or gambling advice.

SkillSpector

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 (1)

Vague Triggers

Medium
Confidence
82% confidence
Finding
This section defines broad intent-detection rules that can switch into betting-recommendation mode for loosely matched phrases such as requests for 'picks' or 'what should I bet on.' If an orchestrator or downstream agent follows these instructions literally, the skill may be invoked or may produce action-oriented gambling advice in cases where the user only wanted general information, increasing the risk of unsafe or policy-sensitive outputs.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.