Security audit

餐饮门店运营数据分析

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language restaurant operations analysis skill with no executable code, persistence, credential access, or hidden data transfer behavior.

Installers should understand this skill is tailored to Chinese restaurant platform operations and may steer responses toward structured business analysis or platform appeal framing. Review appeal drafts for factual accuracy and evidence support before using them with any platform.

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 (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The top-level skill description uses very broad activation phrases covering many ordinary restaurant-operations topics, which can cause the agent to invoke this skill in situations where the user did not intend specialized analysis. Over-broad routing is dangerous because it can override user intent, pull in irrelevant operational heuristics, and increase the chance of inappropriate complaint/appeal guidance being applied outside the intended scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The natural-language description and instructions are written entirely in Chinese and do not state that the user may choose another language. Under the policy, forcing a specific language without opt-in can be a locale policy violation unless the constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The module trigger conditions are phrased loosely (for example, matching any mention of video data, product data, complaints, or planning), so the skill may execute the wrong analytical module based on casual references rather than clear user requests. This can lead to misclassification of user intent and generation of action-oriented recommendations in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The complaint/appeal module is triggered by broad terms like complaints, bad reviews, compensation, and appeals, which are common in normal customer-service discussion and not necessarily requests for adversarial platform dispute drafting. In this context, that is more dangerous because the module contains guidance for rebuttal and appeal framing, so accidental activation could steer the assistant toward defensive or manipulative dispute content without sufficient confirmation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file is entirely written in Chinese and does not provide an opt-in, alternative language, or justification for a locale restriction. Under the policy, a skill artifact that forces a specific language without user choice can constitute a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The entire template library is written as mandatory Chinese copy and response guidance, with no indication that other languages or locales are supported or that the user can opt in to Chinese output. This is a natural-language policy concern because it effectively imposes a specific language across the skill content without documented choice or justified locale restriction.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.