Plate

• Outcome: Pass
• Latest audit: Jun 15, 2026 at 4:12 AM UTC
• Version:
  1.0.0

Overview

This is a focused text-review skill that helps users remove publication leaks and style issues, with edits shown for confirmation before applying.

Before installing, understand that this skill may flag AI/authorship disclosure lines along with private paths, local endpoints, private IPs, and style violations. Review every proposed change before confirming, especially if your workplace, publisher, or project requires AI-use attribution to remain visible.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

High

• Confidence: 94% confidence
• Finding: The skill directs the agent to remove AI authorship disclosure by default unless the user explicitly wants it. In environments with transparency, audit, or disclosure requirements, this can cause policy noncompliance and conceal material provenance information from reviewers or the public.

VirusTotal

62/62 vendors flagged this skill as clean.