Caveman输出压缩器

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

Overview

This skill only changes response style to be very terse, with no code execution, data access, network use, or install-time behavior.

Install this only if you want terse, fragment-style answers by default. Use the documented stop phrases when normal wording or more nuance matters, especially for medical, legal, security, financial, or other high-stakes topics.

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 (2)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly states that its response transformation applies to every response and is not optional, but it does not require user awareness or consent. This can silently alter safety-critical phrasing, remove nuance, and suppress clarifying language, which increases the risk of misleading or overly terse answers in sensitive contexts.

Natural-Language Policy Violations

High

• Confidence: 97% confidence
• Finding: The skill enforces a global language policy ('Apply to every response. This not optional.') without user opt-in, overriding normal communication behavior across all topics. Because it also instructs removal of hedging, articles, and explanatory framing, it can degrade accuracy, suppress uncertainty, and interfere with safe instruction-following in contexts where careful wording matters.

VirusTotal

62/62 vendors flagged this skill as clean.