no-ai-tone

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:44 PM UTC
• Version:
  1.0.0

Overview

This is a prompt-only writing editor that rewrites or audits text, with optional in-place file edits when the user asks for them.

Install this if you want an opinionated text-humanizing editor. Be aware that its style rules are aggressive and subjective, and use --mode edit or --file only on documents you are comfortable letting the agent change.

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: 93% confidence
• Finding: The skill’s activation criteria are intentionally expansive: it triggers not only on explicit user requests, but also on broadly defined situations like producing 'any copy that will be read by real users.' In an agent system, this can cause the skill to attach to many ordinary writing tasks unexpectedly, altering outputs when the user did not request this behavior and increasing the chance of policy drift or interference with other skills.

VirusTotal

62/62 vendors flagged this skill as clean.