ClawHub
Back to skill

Security audit

KlickTipp

Security checks across malware telemetry and agentic risk

Overview

The skill is not malware, but it is marked for review because it presents itself as read-oriented while its only listed KlickTipp actions modify subscriber records.

Install only if you are comfortable with an agent using your OOMOL-connected KlickTipp account to change subscriber records. Before running any action, explicitly confirm the exact email address, action, and intended effect, especially for unsubscribe or tag removal operations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Confidence
97% confidence
Finding
The manifest and description claim this skill is for 'searching and reading data', but the documented actions include state-changing operations such as creating/updating subscribers, unsubscribing contacts, and removing tags. That mismatch can cause an agent or user to invoke the skill under the assumption it is read-only, leading to unintended writes or destructive changes in a marketing system.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The safety section says only actions tagged '[write]' or '[destructive]' change state, but the available actions list does not actually apply those tags to the state-changing operations. This creates a dangerous trust signal: an agent may treat untagged actions as safe reads and execute subscriber creation, unsubscribe, or tag-removal operations without the intended confirmation step.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrase 'Use this skill for ANY KlickTipp request' is overly broad and encourages routing all KlickTipp-related tasks through this skill, even though the skill exposes write-capable actions and the description understates that risk. In context, this broad invocation scope increases the chance of accidental use in situations where a narrower, read-only skill or more explicit action selection would be safer.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.