ClawHub
Back to skill

Security audit

danish-grocery-deals

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it fetches Danish grocery deals and sends the results to a user-configured ntfy notification topic.

Before installing, use a random or authenticated ntfy topic, consider self-hosted ntfy if shopping-interest privacy matters, and only enable the weekly timer if you want recurring automatic notifications.

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
93% confidence
Finding
The skill documentation describes capabilities including local file access, writing attachments, network communication to third-party services, and scheduled execution, but no explicit permission model or warning is declared. This creates a transparency and least-privilege problem: users may authorize or run the skill without understanding that it reads configuration, writes output files, and transmits data externally.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends summaries and full deal-list attachments to ntfy.sh, a third-party notification service, but the high-level description does not prominently warn users about this external data transfer or the privacy implications of public topics. This can expose user interests, shopping habits, configured topics, and historical deal data to unintended parties if defaults are misused or topics are guessable.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The function transmits scraped deal summaries to an external ntfy service with no consent gate, disclosure, or restriction on where the configured URL points. In this skill context, the content is likely low sensitivity most of the time, but the code still enables silent outbound exfiltration to any configured endpoint, which is a meaningful privacy and data-governance risk.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
This code uploads the full text attachment file to the ntfy service automatically if the file exists, again without an explicit disclosure or approval step at the operation point. Because attachments may contain more complete data than the summary, the exfiltration risk is higher than the summary push, even if the intended content is only grocery deals.

Static analysis

No suspicious patterns detected.