Nm Scribe Slop Detector

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:41 PM UTC
• Version:
  1.0.2

Overview

This is a disclosed Markdown-only writing detector with some broad activation and optional edit guidance, but no hidden persistence, credential access, network exfiltration, or destructive behavior was found.

Install only if you are comfortable with a prose-quality skill that may activate on broad writing-related requests. Review its reports as suggestions, confirm before allowing remediation edits, and treat fiction/name and language-detection heuristics as subjective rather than objective proof of AI-generated text.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (2)

Description-Behavior Mismatch

Medium

• Confidence: 90% confidence
• Finding: The skill is presented as a detector, but it explicitly instructs the agent to invoke a separate doc-generation skill with a remediation flag to apply changes. That broadens behavior from analysis into modification, which can cause unintended edits or chained actions a user did not explicitly authorize, especially in automated workflows.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger terms are very broad and generic, including words like writing, cleanup, documentation, and quality. This increases the chance the skill activates during ordinary editing tasks where the user did not ask for AI-slop detection, leading to surprise behavior, overreach, or unwanted content judgments and follow-on actions.

VirusTotal

66/66 vendors flagged this skill as clean.