Security audit

guaikei·小红书数据助手

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only Xiaohongshu public-data helper, but users should understand that it sends requests through guaikei.com and saves fetched results locally.

Install only if you are comfortable sending Xiaohongshu keywords or URLs and your GUAIKEI_API_TOKEN to guaikei.com. Treat the generated logs as retained research data, especially when URLs include xsec_token values or the results include comments and profile metadata.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Confidence: 82% confidence
Finding: The activation text is overly broad: it says the skill should be used even when the user does not explicitly mention Xiaohongshu, as long as the context involves content mining. This can cause the agent to invoke the skill in mismatched contexts, sending user queries to an external third-party API without clear platform intent, increasing unnecessary data disclosure and tool misuse risk.

Missing User Warnings

Medium

Confidence: 76% confidence
Finding: The GET request places the API token and target URL into query parameters, which are more likely to be exposed through intermediary logs, browser/history tooling, reverse proxies, monitoring systems, and referrer-like handling than values sent in headers or POST bodies. In this skill context, the token is a reusable secret and the queried note URL may reveal user research targets, so leakage could enable unauthorized API use or disclosure of user activity.

Missing User Warnings

Low

Confidence: 89% confidence
Finding: The CLI persists the queried profile URL and the full fetched results to a local JSON file, which creates a data-at-rest exposure that users may not expect. Even though the skill is intended for public Xiaohongshu data, the saved URL can include identifiers such as xsec_token values and the result set may contain comments or profile-linked metadata that become accessible to other local users, backups, or log collection systems.

VirusTotal

62/62 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