Security audit

闲鱼运营增长技能

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Xianyu selling guidance skill with no code execution, credential use, persistence, or automatic account actions.

Installers should expect this skill to provide business and marketplace guidance, not to operate Xianyu automatically. Users should still verify current platform, tax, and legal rules themselves and avoid pasting unredacted buyer personal information.

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 (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The activation description uses broad trigger phrases around Xianyu operations, listing, customer service, and data analysis, which can cause the skill to activate in ordinary conversation that only loosely relates to the intended workflow. Over-broad activation increases the chance of unintended routing, context capture, or policy-applying behavior in situations where the user did not actually request this specialized skill.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The router includes vague trigger examples like '能不能做', '怎么回复', or '接下来怎么做' without scope constraints, which can match many unrelated or ambiguous user requests. This makes the skill more prone to accidental activation or incorrect mode selection, especially because the skill covers many high-level business functions and could steer responses based on the wrong workflow.

Static analysis

No suspicious patterns detected.