cultivation-novel-architect

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:41 PM UTC
• Version:
  1.0.0

Overview

This appears to be a creative-writing skill for cultivation fiction, with only a minor risk that its broad trigger wording could activate too often.

Install only if you want cultivation-fiction writing guidance to be applied when relevant. Be aware it may activate on broad genre-related requests, so use explicit wording if you only want casual discussion or analysis rather than the full workflow.

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: 93% confidence
• Finding: The trigger keywords are very broad genre terms, so the skill may activate for ordinary discussion of cultivation fiction rather than only when the user explicitly wants this specialized workflow. This can cause unintended routing, override more appropriate skills, or apply the skill’s assumptions in contexts where they do not fit, reducing safety and predictability of agent behavior.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The instruction to follow the workflow whenever a user requests cultivation-novel content is ambiguous and overbroad, because it lacks precise boundaries for when the skill should take control. In a multi-skill or agentic environment, this can lead to over-invocation, context hijacking, or incorrect handling of user requests that only partially relate to the domain.

VirusTotal

64/64 vendors flagged this skill as clean.