Security audit

guaikei·小红书内容枢纽

Security checks across malware telemetry and agentic risk

Overview

This is a coherent public Xiaohongshu research tool, with the main cautions being third-party API use and automatic local result logs.

Install only if you are comfortable sending Xiaohongshu keywords, URLs, and the Guaikei API token to the Guaikei service, and with successful results being saved locally under logs/. Avoid using private or sensitive links, and periodically delete saved logs if the machine or repository is shared.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The README states that all task results are automatically saved under `logs/` with names derived from time plus keywords/links, but it does not warn that scraped note content, comments, profile URLs, or sensitive research targets may be persisted locally. In a scraping/analysis skill, this increases the risk of unintended retention, disclosure, and secondary misuse of collected public data, especially on shared machines or when logs are later exported or committed.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The document instructs users to provide keywords and Xiaohongshu URLs and to execute data-collection workflows, but it does not warn that these inputs may be transmitted to an external service or used to access third-party platform data. This creates a transparency and consent gap: users may unknowingly send sensitive queries, tracking parameters, or account/profile URLs to the vendor backend, which can lead to privacy, compliance, or policy issues.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The CLI persists the full request and returned results to disk, and both include the profile URL supplied by the user. Because Xiaohongshu profile URLs may contain tracking or access-related query parameters such as xsec_token, this behavior can unintentionally store sensitive identifiers locally without an explicit warning or opt-in, increasing exposure through logs, backups, or shared workstations.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The CLI persists full search output to a local JSON file that includes user-supplied keywords and returned content data, but the user is not clearly warned or asked to opt in. In a data-collection skill like this, silent local retention increases privacy and data-handling risk because sensitive research terms, monitored accounts, or scraped content may remain on disk longer than expected and be accessible to other local users, backups, or logs.

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