Security audit

家庭厨师

Security checks for vulnerabilities and agentic risk

Overview

This is a meal-planning helper whose behavior is mostly disclosed and purpose-aligned, though users should know it stores profile details in plaintext and may send city-based search queries externally.

Before installing, be comfortable with the skill saving household food-planning details, budget, city, and dietary restrictions in a local plaintext file. Also expect recipe and price lookups to use web search, which may expose the search terms and city to the search provider despite the skill's current privacy wording.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:26
Finding: Plaintext Storage of Household Profile Data
Content: View full analysis
Remediation: View remediation

other

Note

Location: SKILL.md:68
Finding: Misleading External-Connectivity and Privacy Claims
Content: View full analysis
Remediation: View remediation

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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The activation description is broad enough to match many generic cooking, recipe, or nutrition questions, which can cause the skill to trigger outside clearly intended boundaries. Over-broad triggering can lead to unnecessary collection or exposure of stored profile data and can override a user's expectation of a general answer rather than a stateful skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The skill is framed specifically for Chinese-language and China-locale usage, including Chinese cities, local grocery platforms, and Chinese cuisine assumptions, without stating that user locale or language preference should be confirmed first. This can cause incorrect searches, culturally mismatched recommendations, and unintended disclosure or processing of user context based on assumptions rather than explicit consent.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.