ZT4AI Self-Audit

Security checks across malware telemetry and agentic risk

Overview

This is a coherent security-audit helper; its broad trigger phrases and local scanning/reporting behavior deserve care but are disclosed and aligned with its purpose.

Install this if you want an agent-assisted local security audit. Run it deliberately, review commands before broad filesystem or network checks, and treat generated audit reports and integrity baselines as sensitive because they may include local file paths, skill names, and security findings.

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: 75% confidence
Finding: The trigger phrases include broad user language such as 'security check', 'am I secure', and 'harden my agent', which can cause the skill to activate in contexts broader than intended. Over-broad activation can unnecessarily expose the skill’s audit instructions and increase the chance of misuse, confusion, or prompt-surface expansion in unrelated conversations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal