Security audit

pan-xiaozi-search

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward web-search helper for pan.xiaozi.cc, with some link-safety and trigger-scope caveats but no hidden execution, persistence, or privileged access.

Install only if you want your agent to search pan.xiaozi.cc for shared cloud-storage links. Treat returned links as untrusted third-party content, avoid entering credentials on linked pages, and make sure searches comply with copyright and your local rules.

SkillSpector

By NVIDIA

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: 86% confidence
Finding: The trigger scope is broad enough to activate on generic requests for files, links, or resources, which can cause the skill to run in contexts the user did not specifically intend. In this skill, that matters because it directs the agent toward searching third-party cloud-share indexes that may surface pirated, unsafe, or sensitive content, increasing the chance of policy-bypassing or risky link discovery.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The metadata description includes multiple generic trigger phrases that overlap with ordinary user language, making accidental or overbroad invocation likely. Because the skill is designed to discover third-party shared cloud storage resources, over-triggering can steer benign conversations into link-finding behavior for potentially infringing or malicious material.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.