Back to skill

Security audit

Secrets (Zero to One)

Security checks across malware telemetry and agentic risk

Overview

This is a business-strategy coaching skill with no executable code or hidden access, with only minor activation-scope and confidentiality considerations.

Reasonable to install if you want startup-idea and business-edge coaching. Because the workflow may discuss proprietary business insights, avoid sharing confidential plans, customer data, or sensitive internal strategy unless you are comfortable using those details in the agent session.

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
93% confidence
Finding
The skill’s activation text uses broad, overlapping business-language triggers such as 'where is our edge' and 'is this idea defensible,' which can match many ordinary strategy conversations. This can cause over-activation and misrouting, making the agent apply the wrong workflow or suppress more appropriate skills, though it does not directly create a security compromise.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.