Novel Publish Ready

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:31 PM UTC
• Version:
  1.0.9

Overview

This skill is a disclosed local novel manuscript checker that scans user-provided text and writes a local results file, with no evidence of hidden network, credential, or destructive behavior.

Install this only if you are comfortable with a local Python script reading manuscript files you choose and creating a local freq_result.txt output. Avoid running it on unrelated private documents, and delete old result files when switching projects if manuscript excerpts are sensitive.

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: 81% confidence
• Finding: The trigger keywords are broad and generic, including common terms like '自检', '大纲', and '人设', which increases the chance of accidental activation in unrelated contexts. Overbroad activation can cause the wrong skill to run, exposing user content unnecessarily and leading to unintended file operations or misleading outputs.

VirusTotal

66/66 vendors flagged this skill as clean.