Security audit

guaikei-rednote-public-data

Security checks across malware telemetry and agentic risk

Overview

This skill is a scoped Xiaohongshu public-data integration with disclosed API-token use and local result logging, though users should handle saved social-media data carefully.

Install only if you are comfortable sending Xiaohongshu keywords or links and the GUAIKEI_API_TOKEN to guaikei.com. Review and delete the generated logs when they contain sensitive research targets, URLs, profile metadata, or comment data, and use the tool only for lawfully accessible public content under applicable platform and privacy rules.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Description-Behavior Mismatch

Medium

Confidence: 90% confidence
Finding: The CLI persists the full fetched Xiaohongshu results to a local JSON file after completing the request. Even if the source data is public, silent local retention increases privacy and data-handling risk because returned results may include profile metadata, comments, or other scraped content that users did not expect to be stored on disk.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The README states that all task results are automatically saved to the `logs/` directory, but it does not clearly disclose that user-supplied search keywords, links, and fetched public content may be persisted locally. This creates a real privacy and data-handling risk because operators may unknowingly store sensitive research targets, campaign plans, or regulated data on disk where it can later be exposed through backups, shared environments, or weak filesystem permissions.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill explicitly guides users to collect public Xiaohongshu notes, comments, and creator posts at scale, but provides no guardrails about privacy expectations, platform terms, lawful basis, or downstream handling of personal data in comments and profiles. Even though the data is described as public, large-scale aggregation and analysis can still create compliance, privacy, and misuse risks, especially for profiling, monitoring competitors, or repurposing user-generated content.

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The CLI writes fetched comment results to a local file automatically, using data derived from the requested URL, without explicit user confirmation or a visible opt-in for persistence. In a skill focused on public Xiaohongshu data, this can still create unintended local retention of scraped content and metadata, increasing privacy, compliance, and data-handling risk if the host environment assumes transient processing only.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The tool writes fetched results to a local JSON log without visible consent or warning to the user. This can create unintended data retention, especially on shared systems or agent hosts where log files may be accessible to other users, backups, or later processes.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The tool silently persists full search results to a local file without clear user disclosure or consent. Even though the queried platform data is public, the saved file can reveal user interests, investigation topics, or operational activity, and may later be accessed by other users, processes, or backup systems.

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