Security audit

guaikei·小红书爆款笔记查找

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu public-data analysis tool that uses guaikei.com APIs and saves results locally, with privacy considerations users should understand before use.

Install only if you are comfortable sending Xiaohongshu keywords, profile links, note links, and embedded URL query tokens to guaikei.com using your GUAIKEI_API_TOKEN. Review and delete the generated logs when the research target, returned data, or competitor-monitoring context is sensitive.

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 (6)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The activation text explicitly says the skill should be used even when the user did not ask for comment analysis, as long as they provided a note link and care about audience feedback. That broad trigger can cause over-collection and disclosure of comment content and commenter metadata to the third-party API without sufficiently explicit user intent, increasing privacy and consent risk.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The main skill documentation does not prominently warn, before use, that note URLs, keywords, and requested content are transmitted to guaikei.com, a third-party service. Without a clear upfront disclosure, users may unknowingly send potentially sensitive research targets or identifiers off-platform, creating data handling and privacy concerns.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The README states that all task results are automatically saved to the logs directory, but it does not clearly warn users that queried keywords, target URLs, and collected platform data may be persisted locally. In a data-scraping and competitor-monitoring tool, these logs can reveal sensitive business research, monitored accounts, or collected third-party content to other local users, backup systems, or accidental sharing.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The CLI writes the full API response object to a local JSON file, and that response may contain sensitive note details, comments, identifiers, or metadata. Persisting this data by default without explicit user consent, disclosure, or access controls increases the risk of unintended local exposure through shared machines, backups, logs, or later exfiltration by other processes.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The CLI forwards the user-supplied Xiaohongshu profile URL, including any xsec_token query parameter, to remote API functions via createPostTask/getPostTask. Because the help text only says the URL is required and does not clearly warn that the full link and token will be transmitted to an external service, users may unintentionally disclose session-like or tracking-sensitive data.

Missing User Warnings

Low

Confidence: 83% confidence
Finding: The skill persists the final output to a local JSON file, and that output includes request metadata such as the queried URL and potentially sensitive profile identifiers or tokens. Writing this data to disk without an explicit notice or redaction increases the chance of accidental disclosure through shared machines, backups, logs, or later file exfiltration.

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:17