ClawHub
Back to skill

Security audit

Gousto Meal Picker

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it uses saved Gousto browser cookies to choose meals and update Gousto orders, with the main risk being live account changes if run without dry-run first.

Install only if you are comfortable giving the skill access to your Gousto session cookies and allowing it to change meal selections on pending orders. Run with --dry-run first, keep gousto-auth.json private with restrictive permissions, and avoid cron automation until you have verified the selections and account behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation explicitly describes where bearer access and refresh tokens are stored in browser cookies and how to extract them, but provides no warning about treating them as secrets or limiting their use. In this skill's context, those tokens grant access to a live Gousto account and can enable account data access and order modification, so exposing handling guidance without security guardrails materially increases the chance of credential misuse or accidental leakage.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The file documents a live PUT endpoint that updates orders, including a complete payload structure and notes on how to preserve relationship fields, but does not warn that this performs real account-changing actions. In an automation skill whose purpose is to select meals automatically, omission of an explicit destructive-action warning makes unintended or unauthorized order changes more likely, especially if an agent or user mistakes the endpoint for a read-only or test operation.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal