ClawHub
Back to skill

Security audit

RevenueCat

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed RevenueCat read-only connector workflow, with some sensitive business data access users should invoke intentionally.

Install only if you intend agents to perform RevenueCat lookups through OOMOL. Treat customer, subscription, and revenue results as sensitive business data, and review any first-time CLI install, login, or account-connection step before allowing it.

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
87% confidence
Finding
The skill description uses an overly broad trigger phrase instructing agents to use it for 'ANY RevenueCat request' and whenever a task 'involves RevenueCat,' which can cause unnecessary or automatic invocation outside narrowly intended read-only contexts. In agentic environments, broad routing language increases the chance of mis-selection, scope creep, and accidental access to sensitive business data such as customers, subscriptions, and revenue metrics.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.