ClawHub
Back to skill

Security audit

mealie-recipe-import

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Mealie recipe importer that uses a user-provided Mealie URL and API token to create recipes, ingredients, units, and cover images as described.

Install only if you trust the target Mealie instance and are comfortable giving the agent a Mealie API token that can create and update recipe-related data. Review Mealie's AI parser configuration before importing private recipe text, images, or internal URLs, because parsing may involve configured external providers.

SkillSpector

By NVIDIA
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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill requires access to environment variables and network connectivity to a self-hosted Mealie instance, but it does not declare those permissions explicitly. This creates a real security transparency issue: users or orchestrators may invoke the skill without understanding that it can read sensitive API tokens from the environment and send authenticated requests over the network.

Missing User Warnings

Low
Confidence
81% confidence
Finding
The README advertises importing recipe text, photos, and URLs into a networked Mealie instance with AI-based ingredient parsing, but it does not clearly warn that recipe content and uploaded images will be transmitted to the Mealie server and may also be sent onward to third-party AI providers configured in Mealie. This is primarily a transparency and privacy issue: users may unknowingly expose personal photos, copyrighted recipe text, or internal URLs/content to external systems.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.