ClawHub
Back to skill

Security audit

Anrok

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed, read-only Anrok connector skill that uses OOMOL's `oo` CLI to access the user's connected Anrok account.

Install this only if you want your agent to read data from your connected Anrok account through OOMOL. Treat returned customer, transaction, filing, and tax data as sensitive, and review any future version carefully if it adds write or destructive Anrok actions.

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
95% confidence
Finding
The trigger phrase says to use this skill for "ANY Anrok request" and "instead of calling the API directly," which is broader than necessary and can force routing of all Anrok-related tasks through a shell-backed connector without additional scoping. Overly broad invocation rules increase the chance the agent will use the skill in contexts involving sensitive data, unexpected actions, or insufficient user confirmation, especially if the skill later expands to include write-capable actions.

Static analysis

No suspicious patterns detected.