Security audit

guaikei·小红书找笔记

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed command-line tool for retrieving public Xiaohongshu data through guaikei.com, with local result logging that users should understand before use.

Install only if you are comfortable sending Xiaohongshu search terms or URLs and your GUAIKEI_API_TOKEN to guaikei.com. Review or delete the generated logs directory if the retrieved public comments, URLs, or business research should not remain on disk.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (6)

Context-Inappropriate Capability

Low

Confidence: 78% confidence
Finding: The error message exposes an out-of-band personal contact channel (`微信: 13395823479`) when token validation fails. While this is not a direct code-execution issue, embedding personal contact details in runtime errors can leak unnecessary operational information, encourage unsafe support flows, and create social-engineering opportunities for users who encounter the error.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The activation language is broad enough to trigger the skill even when the user did not clearly request Xiaohongshu data retrieval, increasing the chance that user prompts, links, or keywords are sent to a third-party API unexpectedly. In this skill's context, that matters because it explicitly relays requests to an external service, so over-triggering can cause unintended data disclosure and user-consent bypass.

Vague Triggers

Low

Confidence: 84% confidence
Finding: The listed 'typical user phrases' are broad and do not provide exclusion conditions, making it easier for the skill to match ambiguous requests and run data collection flows the user may not have intended. While less severe than hidden execution, this still raises privacy and consent concerns because the skill fetches external content and may transmit inputs off-platform.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill notes third-party API dependence but does not clearly disclose that user-provided Xiaohongshu links, keywords, and retrieved content/comments may be transmitted to `guaikei.com`. This can mislead users about where their inputs and retrieved data go, undermining informed consent and creating privacy/compliance risk, especially for monitoring, competitor analysis, or large-scale comment retrieval.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The README states that all task results are automatically saved to a local logs/ directory, but it does not clearly warn users that scraped content, URLs, and potentially sensitive business research data will be persisted on disk. This creates a real data-handling risk because users may assume results are transient, while local files can later be exposed through shared machines, backups, source control, or endpoint compromise.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The CLI writes fetched comment results to a local JSON file named from the target URL, but the user is not clearly warned at execution time that potentially sensitive or regulated third-party content will be persisted on disk. In this skill’s context—large-scale collection of public comments for analysis—silent local retention increases privacy, compliance, and data exposure risk if the workstation is shared, backed up, or later exfiltrated.

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