ClawHub
Back to skill

Security audit

Userlist

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Userlist connector, but it mislabels several create-or-update actions as safe untagged actions, which could let an agent change customer/business data without confirmation.

Review carefully before installing. Use it only for a Userlist account where you are comfortable allowing an agent to create or update users, companies, and relationships through OOMOL. Until the action tags are corrected, treat push_user, push_company, and push_relationship as write actions and require explicit confirmation of the exact payload before running them.

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
92% confidence
Finding
The skill description says to use this skill for ANY Userlist request and instead of calling the API directly, which creates an overly broad trigger surface. That can cause the agent to invoke this skill for loosely related Userlist tasks without sufficient task-specific validation, increasing the chance of unintended reads, writes, or setup actions in contexts where a narrower skill or explicit user confirmation would be safer.

Static analysis

No suspicious patterns detected.