ClawHub
Back to skill

Security audit

guaikei-xhs-get-comments

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu public-data retrieval tool that uses a third-party API and local result logs, with no evidence of hidden credential theft, private-data access, or destructive behavior.

Install only if you are comfortable sending Xiaohongshu keywords, Xiaohongshu URLs, and your GUAIKEI_API_TOKEN to guaikei.com, and remember that returned data is saved locally in logs. Avoid using it for sensitive research targets unless that external processing and local retention are acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The description uses broad trigger language such as invoking on vague references like '红笔记', 'xhs', links, or implied data requests, which can cause the skill to run when the user did not clearly consent to Xiaohongshu scraping or third-party data transmission. This increases the risk of unintended external requests, privacy issues, and data handling outside user expectations.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill does disclose third-party API dependence later in the document, but it lacks a prominent upfront warning near the top where users first learn what the skill does. As a result, users may provide links, keywords, and potentially sensitive business research targets without realizing that this input will be sent to `guaikei.com`.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:16