Security audit

China Beauty Sourcing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a China beauty sourcing reference tool that reads its own bundled data file and does not show hidden, persistent, destructive, or credential-seeking behavior.

Before installing, treat the industry claims as reference material rather than verified live market data, and confirm supplier, regulatory, and certification details independently for business 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

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 86% confidence
Finding: The skill is invocable and explicitly states its logic is implemented in `do.py`, which performs file reads from `data.json`, but the manifest does not declare any tool scope such as `permissions` or `allowed-tools`. This creates an authorization and transparency gap: reviewers and platforms cannot clearly constrain or validate the file access the skill relies on, which can lead to overbroad runtime access or policy bypass depending on the host environment.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: The summary includes Chinese text embedded in otherwise English content ("崛起"), which signals a language/locale assumption without any accompanying opt-in or explanation. Under the policy, forcing or assuming a specific language without user choice can be a natural-language policy concern.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: Entries such as "美博城" appear as untranslated Chinese terms in a data file otherwise written primarily in English. Similar mixed-language usage continues in other lines, which creates a locale-policy issue when no language preference or bilingual-content rationale is specified.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: The file includes labels like "东方美谷", "埭溪镇", and "美妆小镇" in Chinese within otherwise English records, but provides no explicit statement that the dataset is bilingual or China-locale-specific. That can be interpreted as imposing a language choice without opt-in or documented justification.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: The phrase "玻尿酸之都" is presented without translation in a predominantly English file. Because the file lacks any stated locale constraint or user language selection, this mixed-language presentation raises a natural-language policy concern.

Natural-Language Policy Violations

Low

Confidence: 86% confidence
Finding: The module docstring presents the skill as explicitly centered on 'China beauty industry intelligence' and sourcing guidance, which is a locale-specific constraint. In this file, there is no natural-language indication that the user can choose another locale or that the China-only scope is a justified policy/compliance limitation.

Static analysis

No suspicious patterns detected.