ClawHub
Back to skill

Security audit

RiteKit

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed RiteKit connector wrapper with limited command authority and no artifact-backed signs of hidden, destructive, or unrelated behavior.

Install this if you want an agent to use your OOMOL-connected RiteKit account for hashtag and trend-related actions. Be aware that setup may require installing and signing into the oo CLI, and any text, URL, or image URL payloads you provide for actions will be sent through OOMOL/RiteKit.

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 phrase "Use this skill for ANY RiteKit request" creates an overly broad routing rule that can cause the agent to invoke this skill for all RiteKit-related tasks without sufficient specificity. While the skill appears intended for legitimate connector access, broad trigger language can lead to unintended use, reduced opportunity for safer alternative handling, and over-application of the tool in contexts the author did not narrowly define.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.