Security audit

guaikei·小红书热门关键词

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Xiaohongshu public-data tool, with privacy considerations around sending inputs to Guaikei and saving results locally.

Install only if you are comfortable sharing Xiaohongshu keywords, links, and requested public-content targets with the Guaikei API provider. Avoid submitting confidential campaign terms or sensitive URLs unless authorized, and review or delete the generated logs/ files when the results should not persist in the workspace or backups.

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 (4)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill routes user-supplied keywords, links, and potentially retrieved content through a third-party API service, but the top-level description does not clearly warn users of that data flow before use. This can lead users to disclose sensitive URLs, search terms, or analysis targets without informed consent, creating privacy, confidentiality, and compliance risk even if the data is nominally public.

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The README states that all task results are automatically saved to the `logs/` directory, but it does not warn that outputs may contain searched keywords, note URLs with query parameters such as `xsec_token`, comment data, or competitive analysis artifacts. This creates a real data-handling risk because local logs can persist sensitive business intelligence or access-related URL parameters beyond the user's intent and may later be exposed through backups, shared workspaces, or source control.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The CLI persists fetched Xiaohongshu post data to a local JSON file automatically after successful execution, but the interface and help text do not clearly warn users that retrieved content will be stored on disk. This creates a privacy and data-governance risk because scraped public content, comments, or profile-related data may remain in local storage longer than intended, be accessible to other local users/processes, or be ingested into backups and logs.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The CLI writes the searched keyword and full returned results to a local JSON file named with the raw keyword, without any explicit user consent, disclosure in normal execution, or controls over where/how long that data is stored. Because this skill processes potentially sensitive research terms, creator/comment content, and public-account monitoring results, local persistence can unintentionally expose user activity and collected data to other local users, backups, logs, or downstream tooling.

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