Monster Method Decomposition

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:43 PM UTC
• Version:
  1.0.0

Overview

This is a non-executable refactoring guidance skill whose code-editing access matches its stated purpose.

Install this only if you want an agent to help edit and test a codebase during legacy-method refactoring. Use version control, review diffs, and prefer running it on a branch because the skill is intentionally designed to modify source files and tests.

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 (2)

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The discovery triggers include broad natural-language phrases such as 'Developer feels unable to safely change a method', which can match common conversational requests rather than an explicit request to use this skill. That can cause unintended activation and inappropriate tool-enabled editing guidance in contexts where the user only wants discussion or high-level advice.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The manifest description embeds many ambiguous activation phrases like 'where do I even start with this method' and 'can't test this method it's too big', which are common help-seeking statements and may over-trigger the skill. Because the skill operates in full mode with Read/Edit/Bash available, accidental selection can escalate from harmless misrouting into unintended code modification workflows.

VirusTotal

63/63 vendors flagged this skill as clean.