Security audit

guaikei-xhs-comment-list

Security checks across malware telemetry and agentic risk

Overview

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

Install only if you are comfortable sending Xiaohongshu keywords or URLs, plus the GUAIKEI_API_TOKEN, to guaikei.com. Treat the token as a secret, confirm you are allowed to collect the public data you request, and periodically clean the skill's logs directory if stored results are sensitive for your environment.

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 (7)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The description explicitly says the skill should be used even when the user did not say 'collect' or 'scrape,' which creates an overly broad auto-invocation trigger for data extraction. That can cause unintended collection and transmission of user-supplied queries or URLs to a third-party API without sufficiently explicit user intent or consent.

Vague Triggers

Medium

Confidence: 85% confidence
Finding: The 'typical user phrases' are broad conversational prompts like '看看XX最近有什么新内容,' which can match normal research requests without making the data-collection side effect obvious. In context, that raises the risk of silent third-party querying and over-collection when a safer clarification step should occur first.

Missing User Warnings

Low

Confidence: 88% confidence
Finding: The skill acknowledges that data is forwarded through a third-party API, but the warning appears late in a compliance section rather than consistently at invocation points. Users may therefore trigger external transmission of keywords or URLs without timely notice, reducing informed consent and increasing privacy/compliance risk.

Missing User Warnings

Low

Confidence: 92% confidence
Finding: The documentation instructs users to configure `GUAIKEI_API_TOKEN` before running the skill, but it does not mention that this token is a secret or provide any guidance on secure storage, redaction, or avoiding accidental disclosure in logs, screenshots, or shared shell history. In a scraping/data-collection skill that may be used by non-expert operators, this omission increases the chance of credential leakage and unauthorized API use.

Missing User Warnings

Low

Confidence: 87% confidence
Finding: The CLI writes fetched comment data to a local JSON file automatically after successful execution, but the write occurs without an explicit consent step or prominent notice at the point of persistence. Because this skill is designed to collect third-party platform content at scale, silent local retention can create unnecessary privacy and data-handling risk, especially on shared machines or in automated environments.

Missing User Warnings

Low

Confidence: 81% confidence
Finding: The code sends the user-supplied note URL and comment limit to external APIs to create and retrieve a comment collection task, but it does not clearly disclose this transmission at execution time. In a data-collection skill, that omission can mislead users about where their query targets are being sent and processed, which is a privacy and transparency weakness even if the transmitted data is not highly sensitive by itself.

Missing User Warnings

Low

Confidence: 83% confidence
Finding: The CLI writes full search results to a local JSON file named with user-supplied keyword content, but this file creation is not clearly disclosed at runtime before persistence occurs. In this skill’s context, the exported data may contain scraped third-party content or sensitive research targets, so silent local retention increases privacy and data-handling risk if the host environment is shared or logs are collected unexpectedly.

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