Security audit

guaikei·小红书评论获取

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu public-data research tool, with expected network API use and local result logging that users should manage carefully.

Before installing, confirm you are comfortable sending Xiaohongshu keywords/URLs and your GUAIKEI_API_TOKEN to guaikei.com. Use it only for public data, respect platform rules and privacy obligations, limit bulk collection to what you need, and delete or protect the logs/ output when it contains comments, profile data, or sensitive research terms.

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 (4)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The README states that all task results are automatically saved to the `logs/` directory, but it does not clearly warn users that scraped note and comment data will be persisted locally. Because this skill collects third-party content at scale, silent local retention can create unintended data exposure, especially on shared machines, synced folders, or environments with broad filesystem access.

Missing User Warnings

Medium

Confidence: 85% confidence
Finding: The skill explicitly guides users to collect public note details, comments, and competitor/KOL account content at scale, but it provides no safeguards on lawful use, privacy expectations, data minimization, retention, or sensitive-content handling. Even when data is publicly accessible, aggregating and analyzing user-generated content can create privacy, profiling, and compliance risks, especially for comment analysis, competitor monitoring, and KOL screening workflows.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The CLI writes the full fetched detail response, including note data and comments, to a local JSON file by default without any explicit consent, warning, or configuration gate in this file. Because this skill is designed to collect structured Xiaohongshu content for analysis, the output may contain personal data, usernames, comment text, and other sensitive scraped content that can persist on disk longer than the user expects and be exposed to other local users, backups, or downstream tooling.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The CLI writes the full structured search output, including queried keyword and returned content data, to a local file by default without any explicit user consent or warning in this file. In a data-collection skill focused on scraping and analysis, this creates a persistence risk: sensitive research terms, collected public content, or comment datasets may remain on disk longer than intended and be exposed to other local users, backups, or later compromise.

VirusTotal

63/63 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