Detect Ai Flavor

• Outcome: Pass
• Latest audit: Jun 11, 2026 at 11:56 AM UTC
• Version:
  1.2.0

Overview

This is a coherent writing-analysis skill with disclosed URL fetching, but users should treat its AI-authorship judgments as heuristic and avoid private links.

Install this if you want heuristic feedback on whether writing has AI-like style patterns. Do not treat its output as proof of authorship in academic, employment, moderation, or disciplinary settings, and do not submit private drafts or internal/authenticated URLs unless you intend the agent to access and analyze them.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The README states that if a user pastes a URL, the skill will automatically fetch the text, but it does not provide a clear warning about this network action or its privacy implications. This can lead users to disclose internal, authenticated, or sensitive URLs without realizing the system may retrieve remote content, increasing the risk of unintended data access, SSRF-style fetches, or privacy leakage depending on the runtime environment.

VirusTotal

64/64 vendors flagged this skill as clean.