guaikei-xhs-hot-notes

• Outcome: Review
• Latest audit: Aug 12, 2026 · 10:05 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed Xiaohongshu public-data collection tool that uses a third-party API and saves results locally, with privacy considerations users should understand.

Install only if you are comfortable sending Xiaohongshu keywords, note URLs, profile URLs, and your GUAIKEI_API_TOKEN to guaikei.com. Treat the generated logs/ files as potentially sensitive research records, keep them out of shared repos or backups if needed, and delete them when no longer required.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The CLI writes the full search output to a local JSON file named with the user's keyword, which can persist potentially sensitive queries and result data to disk without explicit consent. On shared systems or in automated environments, this can leak user interests, searched terms, and retrieved content through local files or backups.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill sends user-supplied keywords and Xiaohongshu URLs to the third-party guaikei.com-backed API, but the user-facing description and invocation guidance do not clearly warn that this data will be transmitted off-platform before execution. This creates a privacy and consent issue: users may provide sensitive research targets, tracking parameters, or account/profile links without realizing they are being disclosed to an external service.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The README states that all task results are automatically saved under logs/, but it does not warn that filenames or contents may include searched keywords, target profile URLs, note URLs, or other business-sensitive analysis targets. In a tool used for competitor monitoring and marketing intelligence, these logs can expose confidential research activity to other local users, backups, or source-control uploads if not handled carefully.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The CLI writes fetched note details and comments to a local JSON file via log.taskWrite without clearly warning the user that remote content will be persisted on disk. This can create unintended local retention of potentially sensitive or regulated content, especially on shared systems or in automated environments.

Missing User Warnings

Low

• Confidence: 93% confidence
• Finding: Search results are silently written to local storage at the end of execution, but the user-facing flow does not clearly warn at the write site that data will be persisted. This can surprise users and create minor privacy and data-handling risks, especially when queries or results are sensitive.

VirusTotal

63/63 vendors flagged this skill as clean.

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