Caveman Compress Mode

• Outcome: Pass
• Latest audit: Jun 10, 2026 at 12:15 AM UTC
• Version:
  1.0.0

Overview

This appears to be a low-risk communication-style skill, with the main issue being that terse mode may activate too broadly and persist longer than users expect.

Install only if you want a persistent terse-response mode. Be aware that common phrases like asking the assistant to be brief may activate it, and confirm the opt-out command before using it in important or complex tasks.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger phrases are broad enough to activate on common user requests such as 'be brief' or 'less tokens', which can unintentionally switch the assistant into a persistent alternate behavior. Because the mode stays active across later turns until explicitly disabled, accidental activation can silently alter future responses and reduce user control over communication style.

Natural-Language Policy Violations

Low

• Confidence: 91% confidence
• Finding: The skill enforces persistent terse output once triggered and does not automatically revert, which overrides normal conversational choice in subsequent turns. While this is primarily a UX and control issue rather than direct code execution risk, it can degrade clarity, especially in complex or sensitive interactions, and makes accidental activation more harmful.

VirusTotal

64/64 vendors flagged this skill as clean.