Build Protocol

• Outcome: Pass
• Latest audit: Jun 10, 2026 at 5:27 PM UTC
• Version:
  1.0.1

Overview

This skill is a disclosed quality-control workflow for long-form writing and does not show hidden data access, persistence, or destructive behavior.

Install this if you want a rigorous workflow for large writing projects. Be aware it may activate for broad long-form tasks and can make work more heavyweight by adding planning, audit, sub-agent, and publishing checkpoints; use it when that extra process is desired.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The skill description says it triggers implicitly on 'any long-form knowledge production,' which is overly broad for an auto-loaded workflow skill. This can cause the skill to activate in contexts the user did not explicitly request, steering unrelated tasks into a heavyweight multi-agent process and potentially overriding more appropriate task-specific safeguards or workflows.

VirusTotal

64/64 vendors flagged this skill as clean.