ClawHub
Back to skill

Security audit

小红书数据

Security checks across malware telemetry and agentic risk

Overview

The skill matches its stated purpose of fetching public Xiaohongshu data through guaikei.com, but users should understand the third-party API, token use, and saved local result logs.

Install only if you are comfortable sending Xiaohongshu keywords, links, embedded URL parameters, and requested public content identifiers to guaikei.com using your GUAIKEI_API_TOKEN. Treat the token as sensitive, avoid pasting links whose query parameters you do not want shared, and periodically clear the skill's logs directory if saved result data should not be retained.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill requires the sensitive environment variable `GUAIKEI_API_TOKEN`, but there is no explicit permission declaration or prominent trust boundary statement describing that the skill uses external networked functionality backed by a third-party service. This creates a transparency and governance gap: users or platforms may not realize the skill depends on privileged configuration and external API access, which can lead to unsafe deployment or misuse of secrets.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill processes user-supplied Xiaohongshu URLs, query parameters such as `xsec_token`, keywords, and requested content, then sends them to a third-party API service. Although section 10 mentions third-party dependency later, the warning is not prominent near the main description or trigger points, so users may unknowingly disclose browsing targets, tokens embedded in URLs, or research intent to an external service.

Missing User Warnings

Low
Confidence
83% confidence
Finding
The GET request places both the API token and the target URL into query parameters. Sensitive data in URLs can be exposed through proxy logs, browser/history layers, server access logs, monitoring tools, and referrer propagation, making accidental credential disclosure more likely even if the destination is legitimate.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill writes the fetched results to a local JSON file without clearly warning the user beforehand. Even if the source data is public, the output may contain aggregated profile, note, or comment data that can be sensitive in context, and silently persisting it increases the risk of unintended retention, later disclosure, or exposure through shared workspaces, logs, backups, or multi-user systems.

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