Security audit

guaikei-xhs-content-research

Security checks across malware telemetry and agentic risk

Overview

This skill coherently retrieves Xiaohongshu public content through a disclosed third-party API, with local result logging that users should be aware of.

Install only if you are comfortable sending Xiaohongshu keywords, URLs, limits, and your GUAIKEI_API_TOKEN to guaikei.com. Treat xsec_token-bearing URLs and generated logs as sensitive, keep the logs directory out of source control or shared backups, and delete logs when the research task is finished.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Intent-Code Divergence

Low

Confidence: 78% confidence
Finding: The documentation asserts only public-data access and no privacy-data involvement, yet example URLs include xsec_token query parameters that may be sensitive session- or access-associated values. This can mislead users into sharing tokenized URLs without understanding their sensitivity, potentially exposing account-linked access artifacts in logs, shells, or saved files.

Description-Behavior Mismatch

Medium

Confidence: 84% confidence
Finding: The CLI writes fetched Xiaohongshu post results to a local JSON file, creating data persistence beyond the immediate response path. Even if the source data is publicly accessible, saving scraped content locally can increase privacy, compliance, and data-handling risk because it leaves residual copies on disk that may be retained, shared, or accessed unintentionally.

Description-Behavior Mismatch

Low

Confidence: 95% confidence
Finding: The CLI writes the full search output, including the user’s keyword and returned content data, to a local JSON log file. This creates a data-retention behavior not apparent from the skill description and can expose potentially sensitive research queries or scraped content to other local users, backups, or downstream tooling that reads the log directory.

Missing User Warnings

Low

Confidence: 91% confidence
Finding: Automatic saving of task results to the logs directory creates local data persistence without prominent warning about retention, access control, or possible inclusion of URLs, comments, profile data, and tokens. In a scraping/research context, this increases the chance of unintended disclosure through shared machines, backups, support bundles, or source-control commits.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The CLI persists fetched comment results to a local JSON file automatically, but this file does not clearly disclose that behavior to the user before execution. Since comment data may include user-generated content and metadata, silent local storage can create unintended data retention and privacy exposure, especially on shared machines or in automated environments.

Missing User Warnings

Medium

Confidence: 76% confidence
Finding: The tool sends the provided Xiaohongshu note URL and limit parameters to remote APIs to create and fetch a comment task, but this file does not give a clear warning that user input will be transmitted over the network. Even if network use is functionally expected for this skill, lack of transparent disclosure can lead to privacy, compliance, or operational surprises when users supply sensitive or internalized URLs.

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