ClawHub
Back to skill

Security audit

Notilens Clawhub Plugin

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward NotiLens notification plugin that sends user-provided alerts and metadata to NotiLens only when its functions are called.

Install this only if you want task and application events sent to NotiLens. Treat every message, URL, tag, and meta field as data that leaves your environment, and do not include tokens, private prompts, customer data, or sensitive error details unless that is intentional.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly requires environment secrets and is described as a code plugin that sends data to an external service, but it does not declare any tool scope such as permissions or allowed-tools. That omission weakens reviewability and consent by hiding that the skill needs env access and network egress, which increases the chance of unintended secret use or outbound data transmission.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill encourages sending notifications, task events, errors, and arbitrary metadata to NotiLens, but it does not prominently warn users that operational data and possibly sensitive message/meta contents are transmitted to a third-party service. In an agent context, meta fields can easily include run IDs, error strings, URLs, or other sensitive workflow data, so lack of disclosure creates privacy and data-leakage risk.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The manifest explicitly advertises sending task lifecycle events, errors, completions, and metadata to an external service, but provides no warning or guardrails about what data may be included in messages, tags, URLs, or meta fields. In an agent context, those fields can easily carry sensitive prompts, internal state, tokens, filenames, or user data, creating an unreviewed exfiltration path over the network.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The module sends caller-supplied message and metadata fields to an external webhook endpoint with no built-in consent prompt, redaction, allowlist, or disclosure mechanism. In an agent or automation context, this creates a real risk of unintended exfiltration of sensitive task data, errors, URLs, IDs, or user content to a third-party service whenever integrators pass arbitrary payloads into the exported helpers.

Static analysis

No suspicious patterns detected.