ClawHub
Back to skill

Security audit

Grocery

Security checks for vulnerabilities and agentic risk

Overview

This grocery-list skill stores local shopping and pantry notes for its stated purpose and does not show hidden network, purchase, or system-level behavior.

Install only if you are comfortable keeping grocery, pantry, household, and dietary notes in local files under ~/grocery. Ask the agent to confirm before clearing or starting a list fresh, and avoid storing medical-level allergy details or other sensitive information unless you accept the local storage risk.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill specifies that clearing the list will archive history and empty the current list, but it does not require a warning or confirmation before performing this destructive operation. Without a friction step, accidental invocation, misclassification, or prompt overlap in normal conversation can erase the user's active planning state.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The phrases "Clear my list" and especially "Start fresh" are broad natural-language triggers for a destructive action that empties the current list. In a conversational assistant, such generic wording can be matched during ambiguous dialogue or inferred from surrounding context, causing unintended data loss even without malicious input.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill directs creation of persistent local files containing household composition, dietary restrictions, pantry contents, and purchase history, which are sensitive personal data. While writing to local markdown files is not inherently malicious, the lack of any privacy notice, minimization guidance, retention policy, or permission prompt increases the chance users store more sensitive information than necessary and expose it to other local users, backups, or synced folders.

Static analysis

No suspicious patterns detected.