Cca Domain2

Security checks across malware telemetry and agentic risk

Overview

This is a coherent CCA study skill about tool design and MCP integration, with broad local tools disclosed for optional hands-on practice.

Install as a study aid. Use it in a disposable project or git branch for hands-on exercises, and ask the agent to show planned edits before changing files or MCP configuration.

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 (1)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger phrase "工具设计" is broad enough to match ordinary user conversation about tool design, which can cause unintended activation of this skill outside its intended exam-prep context. In a multi-skill environment, overly generic triggers increase routing ambiguity and may surface the wrong instructions or tools, reducing reliability and potentially exposing unnecessary capabilities.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal