ClawHub
Back to skill

Security audit

Gorgias

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Gorgias read/search connector skill, with some sensitive-data and setup cautions but no evidence of malicious behavior.

Install only if you intend to let the agent read data from your connected Gorgias account through OOMOL. Treat ticket, customer, and user lookups as sensitive, confirm ambiguous requests before running them, and run the CLI installer or auth flow only when you explicitly choose to set up OOMOL.

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
89% confidence
Finding
The skill description explicitly says to use this skill for ANY Gorgias request and whenever a task involves Gorgias, which creates an overly broad trigger. This can cause the agent to invoke the skill for incidental mentions of Gorgias rather than only for clear, user-intended Gorgias data access, increasing the chance of unnecessary external queries and unintended data exposure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.