Security audit

Weekly Meal Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local meal-planning skill with some accuracy and language limitations, but no evidence of hidden or harmful behavior.

Install only if a Chinese-oriented, command-line weekly meal planner is acceptable. Treat the costs and shopping list as rough estimates, and run it in a directory where creating or overwriting menu_plan.json is fine.

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

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (6)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: All example user inputs and one expected-output scenario are written in Chinese, and the skill does not state that other languages are supported or give users a language/locale option. This can amount to a language policy issue because the skill appears to assume a specific language by default without opt-in or justification.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The manifest says the skill takes people count, budget, and taste preference to produce a weekly meal plan, implying the budget should influence the generated menu. However, generate_menu uses only taste and people to assemble a fixed 7-day sequence and merely calculates cost afterward, so budget does not affect meal selection at all.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This Python file contains user-facing natural-language strings entirely in Chinese, including the main title, labels, warnings, and save confirmation. Under the policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The title and usage description are written in Chinese, which imposes a language constraint on users. The file does not indicate that the skill is region-specific or provide an opt-in or alternative language, so this appears to violate the language-choice policy.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The docstring says generate_shopping_list creates a shopping list from the menu, and the manifest also promises a shopping list. In practice, the function returns dish names with counts and prices, which is not an actual ingredient-level shopping list and contradicts the documented intent of the function.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.