Security audit

food-safety-legal

Security checks for vulnerabilities and agentic risk

Overview

This is a China-focused food compliance review skill made of Markdown guidance, with no hidden execution behavior or persistence.

Before installing, users should understand this skill is for China food and beverage compliance review and may require sharing proprietary product, label, advertising, producer, or trade details. Redact nonessential personal or confidential information where possible and verify current regulations or consult qualified counsel for high-stakes decisions.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (7)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill explicitly solicits label drafts, images, videos, producer information, and trade-related compliance materials, which can contain sensitive business, personal, or regulated data. While this is functionally relevant to the audit task, the lack of any data-minimization, confidentiality, or safe-handling guidance increases the risk of unnecessary disclosure and improper processing of proprietary information.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The file is written entirely in Chinese and immediately frames its guidance around PRC law for advertising review, without any note that the skill is China-specific or that users may choose another language/locale. Under the policy, forcing a specific language or locale without opt-in can be 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: 87% confidence
Finding: The text states that imported prepackaged foods and additives '应当有中文标签', which is a language requirement presented as a blanket rule in the document. Because this file is a general 'core regulations summary' and does not clearly frame the requirement as applying only within the China regulatory context for imports, it can be read as forcing a specific language without explicit scope clarification.
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 skill file is written only in Chinese and presents its guidance exclusively in that language, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The description is written as a fixed Chinese-language expert service for Chinese food and beverage legal compliance, with no indication that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the constraint is explicitly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: 该技能文件全文以中文编写，并未说明这是面向特定中文用户群体的区域性/合规场景，也未向用户提供语言选择或其他本地化选项。根据规则，若技能强制特定语言而没有用户 opt-in，可能构成自然语言层面的语言/locale 政策违规。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: This markdown file is written entirely in Chinese and provides no indication that language selection is optional or configurable. Under the stated policy, forcing a specific language without user opt-in can constitute a locale/language policy violation unless the constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.