Prompt Optimizer Claude

• Outcome: Pass
• Latest audit: May 29, 2026, 8:44 PM
• Version:
  1.0.0

Overview

This is a prompt-optimization helper with broad activation language but no evidence of hidden access, persistence, credential handling, or harmful behavior.

Install this if you want a helper that rewrites raw prompts into a structured Claude-ready format. Be aware it may activate on general wording like optimize, refine, restructure, or save tokens; edit or disable the trigger if you only want explicit opt-in prompt optimization.

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: 92% confidence
• Finding: The trigger description is broad enough to activate on common editing requests like improving, refining, or restructuring text, which can cause the skill to intercept user intent outside its narrow purpose. Overbroad activation increases the chance of unwanted prompt transformation, hidden instruction injection, or bypass of a user’s preferred workflow, especially in systems where skills auto-trigger based on natural language.

VirusTotal

65/65 vendors flagged this skill as clean.