ClawHub
Back to skill

Security audit

guaikei-kuaishou-search-detail-fetcher

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Kuaishou public-data research skill, with the main caveat that it sends requests to a third-party API and saves fetched results locally.

Install only if you are comfortable sending Kuaishou search terms, profile/video links, and your GUAIKEI_API_TOKEN to the guaikei.com API. Treat the token as a secret, use the tool only for public or authorized research, and periodically review or delete the local logs if collected comments or account data should not be retained.

A.I.G

By Tencent
Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
91% confidence
Finding
The package exposes operational scripts for posting and commenting even though the skill is described as a search/detail-fetching and research tool. This creates a capability mismatch: a user or downstream agent expecting read-only analysis features could invoke write actions against a platform account, leading to unauthorized content publication or engagement activity.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README states that all task results are automatically saved to a logs directory, but the skill’s purpose is to scrape public platform data including comments, video details, and account links. Even if the data is public, automatic local persistence can unintentionally retain personal identifiers, scraped content, and potentially sensitive research targets without informing users about minimization, retention, or access controls.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The README instructs users to configure a GUAIKEI_API_TOKEN but does not warn them to treat it as a secret or avoid exposing it through shell history, shared environments, screenshots, or logs. In a tool that performs networked data collection and automatic logging, weak credential-handling guidance increases the chance of token leakage and unauthorized API use.

Missing User Warnings

Medium
Confidence
77% confidence
Finding
The CLI silently writes fetched comment data to a local JSON file, which can expose collected content to other local users, backups, or later unintended reuse. In a research-oriented skill context, comment data may include personal or sensitive user-generated content, so undisclosed persistence increases privacy and compliance risk.

VirusTotal

62/62 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