ClawHub
Back to skill

Security audit

红笔记内容脉搏

Security checks across malware telemetry and agentic risk

Overview

This skill appears purpose-aligned: it queries public Xiaohongshu data through the Guaikei API and saves results locally, with the main privacy consideration being user awareness of external API use and local logs.

Before installing, confirm you are comfortable sending Xiaohongshu keywords, note/profile URLs, request parameters, and your Guaikei API token to the Guaikei service. Treat the generated logs as potentially sensitive research records and delete or protect them on shared machines.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README instructs users to supply search keywords, note URLs, profile URLs, and comment targets after obtaining a third-party API token, but it does not clearly disclose that these inputs are transmitted to an external service. In a data-extraction skill, this omission is security-relevant because users may unknowingly send potentially sensitive research targets, monitoring subjects, or comment datasets to the vendor, creating privacy, confidentiality, and compliance risk.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The CLI writes the full comment-task output to a local JSON file automatically, using a filename derived from the target URL, without explicit user consent or any visibility control. Because comment data and request metadata may contain sensitive or regulated public-content intelligence, this creates an avoidable local data-retention and exposure risk, especially on shared systems or CI runners.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The CLI writes the full structured search output, including user-supplied query terms and retrieved public-content results, to a local JSON file by default without explicit user consent or a warning. Even though the data is from public Rednote/Xiaohongshu sources, automatic persistence can expose potentially sensitive research activity, monitored keywords, or collected datasets to other local users, backup systems, or downstream tooling that assumes the command is non-persistent.

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:15