ClawHub
Back to skill

Security audit

xianyu-api-client-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Xianyu API client, but it ships credential-like example secrets for an API that can change shop products and orders, so it should be reviewed before installation.

Install only if you need Xianyu shop automation, use a dedicated low-permission Xianyu application key, avoid the bundled example values, and rotate/revoke any credentials matching the published examples. Treat _unsafe methods as automation-only because they bypass the normal confirmation prompt.

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 (1)

T09 · Insecure Skill Coding Practices

Error
Location
config_example.env:4
Finding

Hardcoded Xianyu API Credentials Distributed with the Skill

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
97% confidence
Finding

The example .env file contains what appear to be concrete API credentials rather than obvious placeholders. If these are real or accidentally valid secrets, publishing them can enable unauthorized access to the Xianyu Guanjia API, account misuse, data exposure, or abuse of privileged actions; the skill context increases risk because this client interacts with a real external API and supports automation.

Content

Scanner excerpt · config_example.env (reported line 2)May include surrounding context.

text
# 闲鱼管家API配置示例
# 请将此文件重命名为 .env 并填入您的实际密钥

XIAN_YU_APP_KEY=203413189371893
XIAN_YU_APP_SECRET=o9wl81dncmvby3ijpq7eur456zhgtaxs

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill requires sensitive environment variables (XIAN_YU_APP_KEY, XIAN_YU_APP_SECRET) but does not declare an explicit tool scope such as permissions or allowed-tools. That creates an authorization transparency gap: an agent platform or reviewer may not clearly understand that the skill consumes secrets, increasing the chance of overbroad installation or unintended secret exposure in downstream automation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This Python file contains hard-coded Chinese user-facing confirmation text, such as the high-risk operation prompt and continuation question. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not documented here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

Most of the skill description and operational guidance is written in Chinese, while some security sections are in English, and the document does not state any supported language options or allow the user to choose a preferred locale. This can violate a language/locale policy when skills are expected to respect user language preferences rather than implicitly forcing one.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The natural-language comments at L1-L2 are exclusively in Chinese, which can impose a language requirement on users without any opt-in or justification. The policy requires flagging language or locale constraints when the skill forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.