Back to skill

Security audit

闲鱼运营增长技能

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Xianyu marketplace operations guide with compliance warnings and no hidden code, persistence, or account access.

Installers should expect Chinese-language guidance for Xianyu selling workflows. Treat platform rules, fees, and thresholds as operational references that may need verification against current Xianyu policy, and avoid providing unredacted buyer chats or personal data.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description lists very broad trigger terms such as 闲鱼运营、闲鱼卖东西、闲鱼上架、闲鱼客服、闲鱼数据分析, which can match many ordinary user conversations and cause the skill to activate outside narrow intended contexts. Over-broad activation is dangerous because it can unexpectedly inject this skill’s operating framework into unrelated discussions, increasing the chance of inappropriate guidance, privacy exposure, or policy-sensitive advice being surfaced without clear user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The router uses short, ambiguous trigger phrases like 选品, 帮我分析这个商品, 写标题, 怎么回复, 接下来怎么做 without contextual guards, so many common requests could be classified into this skill even when the user is not asking for Xianyu-specific operational guidance. This is risky because broad routing increases unintended activation and may produce domain-specific recommendations in the wrong setting, especially for conversations that only partially overlap with marketplace selling or customer messaging.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file is written entirely in Chinese and presents itself as the mandatory compliance basis for all operational decisions, but it does not offer any language or locale choice. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

These lines state that the platform algorithm collects user browsing, search, device, and service logs to predict preferences. Under the markdown warning criterion, privacy-impacting behavior should be accompanied by a warning or disclosure, but this section presents the data use operationally without any caution about privacy implications.

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 presents all instructions, examples, and decision frameworks exclusively in Chinese. Under the policy criteria, forcing a specific language without user opt-in or an explicit documented justification is 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
89% confidence
Finding

This markdown file presents all instructions, examples, and constraints exclusively in Chinese. Under the policy rule for language or locale constraints, forcing a single language without user opt-in or an explicit documented justification 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
92% confidence
Finding

This markdown file presents all instructions, warnings, and examples exclusively in Chinese, with no indication that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

L016-L018明确说明闲鱼不单独展示点击量,且L017指出“搜索曝光 vs 推荐曝光”无法获取,要求不要编造数据。但L116和L122又指导用户区分搜索曝光低与推荐曝光低并据此诊断,形成直接的文档内意图矛盾。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The instruction at L148 says the assistant 'must answer' in the shown format, and the entire mandated template content is in Chinese. This imposes a specific language/locale in the skill's natural-language behavior without any opt-in or alternative language path for users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The entire skill reference is written only in Chinese and does not indicate that language selection is optional or that the skill is intended exclusively for a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown skill content forces a specific language for all users, and there is no opt-in, alternative language, or explicit justification that the document is restricted to a Chinese-language audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file contains all user-facing guidance in Chinese and does not indicate that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language locale constraint and applies to all file types.

Content

No source excerpt is available for this finding.