Security audit

guaikei-xhs-look-up

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent public Xiaohongshu data lookup tool, with expected third-party API use and local result logging that users should understand before installing.

Install only if you are comfortable sending Xiaohongshu keywords or URLs and request metadata to guaikei.com with your GUAIKEI_API_TOKEN. Treat returned notes, comments, creator data, and generated logs as retained local data; delete artifact/logs when no longer needed and avoid using sensitive URLs or regulated datasets in shared environments.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Description-Behavior Mismatch

Low

Confidence: 93% confidence
Finding: The README frames the skill as a lookup/analysis tool, but it also states that all task results are automatically persisted under a local logs directory. For a data-collection skill, this creates an undisclosed data-retention surface: searched keywords, target profile URLs, note details, and comments may remain on disk longer than users expect and could be exposed to other local users, backups, or downstream tooling.

Description-Behavior Mismatch

Medium

Confidence: 92% confidence
Finding: The CLI writes the full fetched result set, including note details and comments, to a local JSON file after already returning the data to stdout. This creates an additional at-rest copy of potentially sensitive or regulated scraped content without clear user consent or a stated retention policy, increasing exposure through local disk access, backups, shared workspaces, or later exfiltration.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The CLI writes full comment results to a local JSON file, which creates data persistence of scraped third-party content without clearly informing the user. On shared systems or automated environments, this can expose collected data to unintended parties and increase privacy/compliance risk because users may assume output is only sent to stdout.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The tool sends the supplied note URL and query parameters to an external API using the configured token, but it does not clearly disclose that user-supplied data is transmitted off-host. Although remote processing is expected for this skill, lack of explicit disclosure can cause unintentional sharing of sensitive URLs, tracking parameters, or workflow metadata in enterprise or regulated environments.

Missing User Warnings

Low

Confidence: 88% confidence
Finding: The CLI writes the full search output to a local JSON file whose filename includes the user-supplied keyword. This creates a privacy and data-retention risk because scraped/search-derived content and query terms may be persisted on disk without explicit user consent, visibility, sanitization guarantees for the filename, or an option to disable logging.

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