QRdex

• Outcome: Pass
• Latest audit: May 28, 2026, 4:48 AM
• Version:
  1.0.0

Overview

QRdex is a coherent QRdex.io API helper, with expected account-level QR management risks but no evidence of hidden or malicious behavior.

Install only if you want an agent to use your QRdex.io account. Use a revocable API key if available, confirm IDs before update or delete actions, and avoid creating tracked QR codes or QR payloads containing WiFi passwords, phone numbers, messages, or other sensitive data unless that storage and exposure are acceptable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill documents use of environment variables and outbound network access but does not declare permissions or capability boundaries. This can cause the agent platform or user to invoke a networked, credential-using skill without clear visibility into what resources it needs, increasing the chance of unintended data access or transmission.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The description is broad enough that an orchestrator may select this skill for many generic QR-related requests without strong trigger boundaries. Because the skill performs authenticated external API actions, overly broad invocation increases the risk of unintended creation, modification, deletion, or disclosure of QR resources.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The documentation states scan tracking is enabled by default but does not warn that this may collect analytics or personal data about people scanning the QR code. In a QR-management context, silent default tracking can create privacy, consent, and compliance issues, especially if users generate codes for third parties without understanding the telemetry implications.

Missing User Warnings

Low

• Confidence: 78% confidence
• Finding: The skill exposes delete functionality without a warning or confirmation note, which can make destructive API actions easier to trigger accidentally. Even though deletion is described as soft-delete, unintended removal can still disrupt operations, hide assets, or require recovery work.

Missing User Warnings

Medium

• Confidence: 82% confidence
• Finding: The API enables scan tracking by default without any privacy notice or explicit opt-in guidance, which can cause agents or users to create trackable QR codes unintentionally. In the context of a QR generation skill, this is meaningful because scan telemetry may collect behavioral or location-adjacent metadata and create privacy/compliance risk if used without informed consent.

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The delete command performs a destructive API operation immediately with no confirmation prompt, dry-run option, or force flag. In a CLI used by agents or humans, this increases the chance of accidental deletion of QR codes, especially when IDs are mistyped or commands are generated automatically.

VirusTotal

60/60 vendors flagged this skill as clean.