guaikei·小红书笔记·评论·博主

• Outcome: Pass
• Latest audit: Aug 16, 2026 · 1:48 AM UTC
• Version: 1.0.0

Overview

This skill is a coherent Xiaohongshu public-data lookup integration, with expected external API use and local result logs that users should understand before installing.

Install only if you are comfortable sending Xiaohongshu keywords, URLs, and requested public data to Guaikei and storing successful results locally in logs/. Treat GUAIKEI_API_TOKEN as a secret, avoid sharing terminal output that may reveal query details, and periodically delete logs if they contain sensitive research or creator data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (8)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill states that every execution result is automatically saved to `logs/`, including timestamps and keyword or link identifiers, but this retention is not surfaced as a prominent user warning. That creates a privacy and data-handling risk because user-supplied URLs, search terms, and retrieved Xiaohongshu content may persist locally without informed consent and may later be exposed to other local users, backups, or tooling.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill depends on a third-party API service and the content indicates that user queries and target links are sent externally, but this is not clearly and prominently disclosed before use. Users may provide sensitive competitor research terms, creator profile URLs, or note links without realizing those inputs and the fetched data are being transmitted to an external vendor.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The README states that all task results are automatically saved to the `logs/` directory, but it does not warn users that scraped note content, comments, creator data, or derived outputs may be stored persistently on disk. In a data-scraping context, silent persistence increases the risk of unintended retention, local disclosure, and mishandling of third-party content, especially on shared systems or when logs are later redistributed.

Missing User Warnings

Low

• Confidence: 87% confidence
• Finding: The documentation instructs users to configure `GUAIKEI_API_TOKEN` before execution but does not warn that the token is sensitive or that it must not be echoed, logged, hardcoded, or included in outputs. In an agent/tooling context, missing this guidance can lead to accidental credential disclosure through terminal history, debug output, chat transcripts, or generated examples.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The token and request parameters are placed into a GET request query string, which can be exposed through browser history, intermediary proxy logs, server access logs, monitoring tools, and referrer leakage. Even if HTTPS is used, query-string secrets are commonly retained in multiple systems, increasing the chance of credential disclosure and unauthorized API access.

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The CLI persists fetched results to a local JSON file automatically, without clear user consent or warning. Because the output may contain scraped creator data and metadata, this creates a privacy and data-retention risk on shared systems or environments where local files are later exposed, indexed, or collected by other processes.

Missing User Warnings

Medium

• Confidence: 80% confidence
• Finding: The tool sends the provided URL and parameters to an external API service, which is expected for this skill, but it does so without an explicit disclosure to the user. In a data-collection skill, silent transmission to a third party can create privacy, compliance, and trust issues, especially if users assume processing is local or do not realize URLs and query tokens are being relayed.

Ssd 3

Medium

• Confidence: 96% confidence
• Finding: Automatic archival of execution results to local log files can retain user-provided links, search keywords, and returned Xiaohongshu content beyond the immediate task. In a plain-language workflow, this persistence increases the chance of unintended disclosure through shared workstations, loose filesystem permissions, backups, or later reuse by unrelated processes.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.