ClawHub
Back to skill

Security audit

GenPage

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent GenPage connector, but it under-labels some account-changing actions as safe direct actions.

Review the exact GenPage action and payload before allowing writes. In particular, treat linking or unlinking audiences and campaigns as account-changing operations even though this artifact does not tag them as write actions. Only run the oo CLI install or login steps if you trust OOMOL and intended to connect this GenPage account.

SkillSpector

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 description says to use this skill for "ANY GenPage request" and "instead of calling the API directly," which is an overly broad trigger for automatic invocation. Broad routing language can cause the agent to select this skill in situations where a narrower or safer tool would be more appropriate, increasing the chance of unintended reads, writes, or destructive operations against GenPage.

Static analysis

No suspicious patterns detected.