ClawHub
Back to skill

Security audit

Qfc Order

Security checks for vulnerabilities and agentic risk

Overview

This skill automates a QFC pickup cart in a logged-in browser and its sensitive behavior is mostly disclosed and aligned with that purpose, but users should review its local order-state storage and checkout confirmations.

Before installing, be comfortable letting the skill operate in a logged-in QFC browser tab and save local order-state details. Review the cart, pickup slot, total, and any final submit action yourself, and clear qfc-state.json after ordering if you do not want shopping or transaction metadata retained.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly persists order state, including store, cart items, scheduled pickup slot, and potentially order ID and total, to a local JSON file without any visible user-facing disclosure, consent flow, retention policy, or minimization guidance. In a grocery-ordering context, these details can reveal shopping habits, location preferences, and transaction metadata, creating unnecessary privacy exposure if the file is accessed by other skills, users, or processes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.