ClawHub
Back to skill

Security audit

Rotifer Guide

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Rotifer developer helper skill, with ordinary caution needed around broad trigger wording and unpinned npm commands.

Install this if you intend to use Rotifer. Use explicit prompts that mention Rotifer or Genes, review any generated scaffold before publishing or submitting it, and consider pinning npm package versions or Git tags before running install/build commands in sensitive environments.

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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The README advertises very broad natural-language triggers such as "create", "find", "diagnose", and "upgrade" without clear disambiguation rules or scope boundaries. In an agent environment, this can cause the skill to activate on common user requests unintentionally, leading to confused-deputy behavior, unexpected tool use, or the skill handling requests outside its intended security envelope.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill advertises activation on very broad phrases such as "make a", "new", "check", "search", and "upgrade", which are common in unrelated conversations. In an agent environment, this can cause unintended routing into this skill and lead to execution or suggestion of Rotifer CLI/npm commands in the wrong context, increasing the chance of accidental package installation, command execution, or user confusion.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The intent router maps vague user signals like "why", "check", "search", "find one that does XX", and "new" directly to operational sub-capabilities without enough specificity checks. Because the skill contains actionable shell commands and package-install guidance, ambiguous routing can escalate a casual query into operational advice that is unrelated to the user's actual intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal