guaikei·小红书笔记与评论

• Outcome: Review
• Latest audit: Aug 15, 2026 · 1:33 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed Xiaohongshu public-data retrieval tool that uses a third-party API token and saves results locally, with no evidence of hidden or destructive behavior.

Install only if you are comfortable sending Xiaohongshu search terms, note/profile URLs, and xsec_token query strings to guaikei.com using your GUAIKEI_API_TOKEN. Also expect successful runs to leave JSON result files in the skill's logs directory, so avoid sensitive research terms on shared systems or clean up logs when needed.

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
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (9)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 82% confidence
• Finding: The skill requires access to an environment secret (`GUAIKEI_API_TOKEN`) but does not declare explicit permissions or prominently scope how that secret is used. This creates a transparency and governance gap: the skill can transmit user queries and links to a third-party API using a hidden credential, making review and policy enforcement harder.

Description-Behavior Mismatch

Low

• Confidence: 89% confidence
• Finding: The CLI writes fetched comment data to a local JSON file automatically after successful execution. Even if the source content is public, persisting results expands the data exposure surface by creating at-rest copies that may contain user-generated text, metadata, or analyst research artifacts not implied by a simple return-only tool flow.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The description contains broad implicit triggers such as activating even when the user does not explicitly mention Xiaohongshu or data, which can cause the skill to run on ambiguous requests. This increases the chance of unintended third-party data transmission, mistaken tool use, and over-collection beyond user expectations.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The documentation discloses third-party API externalization only near the end, while the main usage flow and examples encourage immediate execution with user-provided keywords and links. Users may unknowingly send potentially sensitive URLs, tokens in query strings, or research intent to an external service without an upfront notice or consent checkpoint.

Missing User Warnings

Low

• Confidence: 83% confidence
• Finding: The tool writes fetched comment results to disk without explicit user consent or a clear warning at the point of use. In this skill's context, the data is intended to be returned as structured public XHS data, so silent local persistence can surprise operators and increase retention/privacy risk on shared systems.

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: This CLI transmits the user-supplied note URL and limit to a remote API and then persists detailed returned data to local disk, but it does not provide an explicit consent or warning at execution time about network transmission and storage. In a data-collection skill, this increases the risk of unintentional disclosure, especially if users assume processing is local or do not expect scraped results and metadata to remain on disk.

Missing User Warnings

Medium

• Confidence: 79% confidence
• Finding: The tool persists API-derived results to a local JSON file without clearly warning the user in this file. Even though the skill targets public Xiaohongshu data, the saved output may contain scraped profile/content metadata that remains on disk longer than intended and could be exposed to other local users, backups, or downstream tooling.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The CLI persists the searched keyword and full search results to a local JSON log file, which can expose potentially sensitive research topics, targets, or collected third-party content to other local users, backups, or later processes. In this skill’s context, users may run competitor analysis or KOL monitoring queries that are business-sensitive, so silent disk persistence creates an avoidable confidentiality risk even if it is not overtly malicious.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The tool sends user-provided search keywords to an external API using an API token, but does not clearly disclose that the query data will leave the local environment. While network transmission is expected for this kind of search skill, the lack of explicit notice can lead users to unintentionally submit sensitive internal research terms or monitoring targets to a third-party service.

VirusTotal

64/64 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:17