Security audit

小红书精选

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Xiaohongshu public-data retrieval tool, with expected third-party API use and local result logging disclosed enough to review before use.

Install only if you are comfortable sending Xiaohongshu keywords, note/profile links, and your GUAIKEI_API_TOKEN to guaikei.com. Review and clean the local logs directory if the searches or fetched public content are sensitive business research or should not persist on the machine.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Context-Inappropriate Capability

Medium

Confidence: 90% confidence
Finding: The CLI writes the full search output, including the user's query and returned Xiaohongshu data, to a local JSON file without any opt-in or retention controls. This creates a data exposure risk on shared systems or environments where local artifacts are collected, synced, or readable by other users/processes, and it exceeds the stated behavior of merely returning structured data.

Vague Triggers

Medium

Confidence: 82% confidence
Finding: The trigger description is intentionally expansive, including cases where the user did not explicitly ask for Xiaohongshu data retrieval and where mere mention of related terms or links can activate the skill. This can cause unintended invocation and silent exfiltration of user-supplied keywords or URLs to a third-party service, which is more concerning because the skill explicitly depends on an external API.

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 saved artifacts may include searched keywords, supplied note/profile URLs, fetched public content, and possibly derived analysis outputs. Even when scraping only public data, silent persistence increases the chance of retaining sensitive business research, user-provided targets, or regulated content on disk where it may later be exposed, shared, or collected by other processes.

Missing User Warnings

Low

Confidence: 83% confidence
Finding: The tool silently writes search results to a local file after completing the command, but the help text and normal output do not clearly warn the user that a file will be created. Even if the data is public-source content, unexpected persistence can leak research activity, keywords, and collected results to local disk, backups, or other users on the host.

VirusTotal

64/64 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