cpp-pro

Security checks across malware telemetry and agentic risk

Overview

This is a C++ coding-assistant skill with broad but disclosed project-analysis and implementation guidance, and it contains no executable install code or hidden data handling.

Install this if you want a general C++ assistant, but use it only on repositories you are comfortable letting an agent inspect. Review any proposed code or build-system changes before applying them, and require actual compiler, sanitizer, test, and benchmark output before trusting performance or safety claims.

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: 87% confidence
Finding: The skill’s activation guidance is broad and underspecified, describing general C++ development behavior without defining clear trigger phrases, scope boundaries, or refusal conditions. In an agent system, this can cause the skill to activate in unintended contexts and perform expansive project analysis or code modification beyond user intent, increasing the chance of overreach or unsafe tool use.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal