Nạp liệu

• Outcome: Pass
• Latest audit: Jun 19, 2026 at 2:33 AM UTC
• Version:
  1.0.1

Overview

This is a text-only adult-fiction rewriting skill with explicit purpose and no evidence of code execution, data access, persistence, or hidden behavior.

Install only if you want an 18+ fiction rewriting helper. Use it on clearly adult, consenting fictional material and review outputs carefully, because its broad patterns may sexualize scenes that were originally non-explicit.

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 (3)

Vague Triggers

Medium

• Confidence: 97% confidence
• Finding: The trigger definition for Pattern 0 applies to every chapter and instructs automatic erotic augmentation of titles, creating an extremely broad activation surface. In the context of a transformation skill that converts clean content into explicit sexualized material, this ambiguity is dangerous because it can cause unconditional invocation and bulk unsafe rewriting rather than context-limited behavior.

Vague Triggers

Medium

• Confidence: 98% confidence
• Finding: Pattern A matches very common conversational phrases like whispering near an ear, then mandates insertion of explicit sexual touching and stimulation. Because these phrases are common in ordinary fiction, the trigger can fire on benign scenes and escalate them into explicit sexual content without reliable boundaries, making unintended activation highly likely.

Vague Triggers

Medium

• Confidence: 97% confidence
• Finding: Pattern B targets a broad class of common affectionate actions like holding an arm or tugging clothing, then replaces them with explicit sexual behavior. This creates a high-risk semantic overreach: innocuous interactions can be transformed into sexual content, which is especially dangerous because the skill's stated purpose is to convert clean stories into 18+ material while preserving plot, encouraging widespread misuse across many passages.

VirusTotal

63/63 vendors flagged this skill as clean.