Security Audit Pro

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed security-audit guidance skill with no executable code, though it may involve sensitive project or cloud information when used.

Install only if you intend to let an agent review security-sensitive project, dependency, container, or cloud configuration context. Provide scoped targets and avoid sharing production credentials unless the audit task truly requires them.

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
89% confidence
Finding
The trigger phrases are generic and action-oriented without clear scope limits, so the skill may activate in situations broader than the user intended. In a security-audit skill, unintended invocation can cause unnecessary scanning behavior, sensitive-context handling, or overbroad audit responses in unrelated conversations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal