ClawHub
Back to skill

Security audit

Readwise

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Readwise connector helper that uses the OOMOL CLI for account-scoped Readwise actions, with write actions explicitly requiring user confirmation.

Install this if you are comfortable using OOMOL as the intermediary for your Readwise account. Confirm payloads carefully before any create, save, or update action, and only run the one-time CLI install or account connection steps when you intentionally want this integration configured.

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
94% confidence
Finding
The skill description says to use this skill for ANY Readwise request and whenever a task involves Readwise, which creates an overly broad trigger that can capture a wide range of user intents without clear scoping. In practice, this increases the chance the agent will invoke a tool-capable skill unnecessarily, including for ambiguous mentions of Readwise, and because the skill exposes write actions, misrouting can lead to unintended state changes or premature action planning.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.