ClawHub
Back to skill

Security audit

Recurly

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly scoped Recurly connector that can read and change billing-related data, with write actions disclosed and requiring user confirmation.

Install this only if you want your agent to access Recurly through OOMOL. Treat read actions as sensitive because they may expose customer, account, subscription, and billing data, and review every write payload before approving changes.

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
90% confidence
Finding
The description says to use this skill for ANY Recurly request, including reading, creating, and updating data, which creates an overly broad trigger surface. In an agentic environment, this can cause the skill to be invoked for loosely related requests and route sensitive billing or subscription operations through a powerful integration, increasing the chance of unintended data access or state-changing actions.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.