Olive Skill

• Outcome: Pass
• Latest audit: Jun 8, 2026 at 4:50 PM UTC
• Version:
  1.0.0

Overview

The skill appears to be a broad advisory prompt skill with no evidence of hidden execution, credential access, persistence, or data exfiltration.

Install this as a general-purpose advisory skill only if you want it to shape reasoning and communication across a wide range of tasks. If you need strict domain-specific policy handling, use it alongside narrower specialist skills and keep task-specific instructions explicit.

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: 88% confidence
• Finding: The skill description is broadly scoped to common reasoning domains like risk, responsibility, authority, technology, learning, collaboration, and public communication, which can cause it to activate in many ordinary tasks. That over-breadth can let persona-conditioning override task-specific instructions or evidence handling in contexts where the skill was not intended, increasing the chance of biased or misaligned outputs.

VirusTotal

64/64 vendors flagged this skill as clean.