qsnctf-practice-dynamic

Security checks across malware telemetry and agentic risk

Overview

This skill is a small, read-only QSNCTF lookup helper that fetches public leaderboard and activity data from disclosed endpoints.

Before installing, note that the skill contacts www.qsnctf.com and may require installing Python requests. Use a trusted Python environment for the dependency, and install only if you are comfortable sending lookup requests to that public QSNCTF service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill explicitly documents outbound HTTP requests to qsnctf.com APIs, yet no permissions are declared. This creates a transparency and policy-enforcement gap: users and the hosting platform may not realize the skill performs network access, which can weaken consent, auditing, and sandbox controls even if the target API itself appears benign.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal