Security audit

ym-fridge-weekly-menu

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent text-only meal-planning skill with no hidden execution, network use, persistence, or privileged access.

Before installing, note that the skill may activate on broad food-related phrases and its output template is in Chinese. It does not appear to run code, access accounts, persist changes, or send data elsewhere.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrase "今天吃什么" is extremely broad, common conversational language that can appear in many everyday contexts unrelated to this skill. This increases the chance of unintended activation, causing the agent to route users into this skill when they did not intend menu planning, which can degrade reliability and potentially expose user-provided context to an unnecessary skill path.

Vague Triggers

Medium

Confidence: 97% confidence
Finding: The trigger phrase "冰箱食材" is too short and underspecified, making it likely to match incidental mentions rather than explicit requests to generate a weekly menu. Overbroad activation can cause misrouting, accidental invocation, and unnecessary processing of user context in a skill the user did not intend to use.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The entire template and its required filled content are specified in Chinese, with no indication that users may choose another language or locale. This is a natural-language policy issue because it imposes a specific language by default rather than offering an explicit user choice.

Vague Triggers

Low

Confidence: 92% confidence
Finding: The trigger phrase "今天吃什么" is extremely broad, common conversational language that can appear in many everyday contexts unrelated to this skill. This increases the chance of unintended activation, causing the agent to route users into this skill when they did not intend menu planning, which can degrade reliability and potentially expose user-provided context to an unnecessary skill path.

Static analysis

No suspicious patterns detected.