YES.md

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:18 PM UTC
• Version:
  1.1.1

Overview

This is a broad workflow-governance skill that pushes the agent to verify work and avoid guessing, with no executable payload or hidden data behavior found.

Install this if you want a strong process guardrail that may activate often. Keep approval prompts enabled for shell commands, deployments, database changes, and edits involving sensitive configuration or credentials.

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

High

• Confidence: 94% confidence
• Finding: The trigger description is extremely broad and applies to nearly any non-trivial engineering task, including routine debugging, implementation, configuration, deployment, and follow-up verification. This can cause the skill to activate pervasively and override normal task-specific behavior, creating a governance choke point that may degrade agent autonomy, increase unnecessary file/system actions, and amplify the effect of any bad instruction embedded in the skill.

VirusTotal

65/65 vendors flagged this skill as clean.