ClawHub
Back to skill

Security audit

Writer

Security checks for vulnerabilities and agentic risk

Overview

This Writer connector skill is coherent and disclosed, with narrow tool access and user confirmation required before write actions.

Install this only if you intend to let your agent use your OOMOL-connected Writer account. Review payloads before approving chat completion requests because they may send conversation text to Writer and may consume account credits; do not run the setup commands unless the oo CLI or connection is actually missing.

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
90% confidence
Finding
The description instructs the agent to use this skill for "ANY Writer request," creating an overly broad routing rule that can cause the skill to be invoked for a wide range of tasks without clear scoping or safety boundaries. Because the skill includes both read and state-changing actions, broad invocation increases the chance of unintended tool use, especially when a request only loosely relates to Writer or when safer/more specific handling would be appropriate.

Static analysis

No suspicious patterns detected.