Caveman Help

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple one-shot help card for caveman-mode commands, with only a minor risk of accidental trigger wording.

Install this if you want a quick reference for caveman-mode commands. Prefer explicit slash commands where possible, because ordinary phrases like "normal mode" could be interpreted as mode controls in the broader caveman system.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The deactivation phrases "stop caveman" and especially "normal mode" are broad enough to appear in ordinary user conversation, which can unintentionally disable the mode or alter behavior without clear user intent. In a skill that changes assistant response style across a session, ambiguous triggers create a prompt-routing/control risk because unrelated text can cause state changes.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal