ClawHub
Back to skill

Security audit

xhs-blogger-posts

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu public-data lookup tool, with notable but purpose-aligned risks around third-party API use and automatic local result logs.

Install only if you are comfortable sending Xiaohongshu keywords or links and your GUAIKEI_API_TOKEN to the third-party guaikei.com API. Review or delete the generated logs directory if results include sensitive research topics, competitor targets, or comments you do not want retained locally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The CLI persists full search output to a local file using a filename derived in part from user input. Even though this is not obviously malicious, it introduces unintended local data retention beyond the tool’s stated read/search behavior and can expose search history and returned content to other local users, backups, or downstream processes. The skill context makes this somewhat more sensitive because search terms and results may reveal user research interests, competitor analysis, or account targeting activity.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The GET request places the API token in query parameters, which are more likely to be exposed through logs, browser history, proxy records, monitoring systems, and referer leakage than headers or POST bodies. In this skill context, the token is a credential for a third-party data service, so exposure could enable unauthorized API use or account abuse.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The code returns a hard-coded error message that directs users to a specific WeChat contact and assumes Chinese-language support when authentication fails. This is risky because it creates an unsolicited off-platform contact path, may leak support routing not approved by the platform, and can pressure users into contacting a personal channel rather than a trusted in-product or documented support process.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The CLI persists fetched note details and comments to a local JSON file automatically, which can retain potentially sensitive or regulated data on disk beyond the user's immediate session. In this skill's data-collection context, silent persistence increases privacy and data-handling risk because operators may not realize public scraped content, metadata, or comments are being stored locally and may later be exposed via backups, shared workstations, or repository commits.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.