ClawHub
Back to skill

Security audit

ReferralHero

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed ReferralHero connector wrapper with clear warnings for actions that create, update, or delete data.

Before installing, understand that this skill can modify or delete ReferralHero subscriber and campaign data through your connected OOMOL account. Review payloads carefully and only approve write or destructive actions when the target and effect are clear.

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
93% confidence
Finding
The phrase 'Use this skill for ANY ReferralHero request' is an overly broad routing instruction that can cause an agent to invoke this skill for all ReferralHero-related tasks without first evaluating whether the request is appropriate, safe, or within least-privilege boundaries. In this skill, that risk is amplified because the skill includes write and destructive actions, so a broad trigger can steer sensitive operations through a path that may execute state-changing commands if downstream safeguards fail or are bypassed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.