ClawHub
Back to skill

Security audit

Kuaishou Guaikei Content Research

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Kuaishou public-data research tool, with expected network API use and local result logging but no evidence of account posting, hidden execution, or destructive behavior.

Install only if you are comfortable sending Kuaishou keywords or URLs to guaikei.com with a GUAIKEI_API_TOKEN and storing returned public-data JSON locally in logs. Review and delete logs when working on shared machines or sensitive research.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (5)

Context-Inappropriate Capability

Medium
Confidence
89% confidence
Finding
The package is described as a research and analytics tool, but it exposes CLI commands for posting and commenting, which are account-action capabilities not disclosed by the stated purpose. This mismatch can mislead users and reviewers about what the skill can do, increasing the risk of unauthorized social-media actions, spam, or abuse once credentials are provided.

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The declared purpose emphasizes analytics, monitoring, and research, yet the package entry points include commands that can perform actions on a user account. In a skill ecosystem, this capability gap is dangerous because users may consent to a seemingly passive analysis tool while actually installing tooling that can publish content or interact with third parties.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The README states that all task results are automatically saved to the `logs/` directory, but it does not clearly warn users that fetched content, URLs, comments, or derived analysis outputs may persist on disk. For a data-collection tool, silent persistence increases the risk of unintentionally storing sensitive or regulated data locally, which can later be exposed through backups, shared machines, or accidental commits.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The CLI writes the full comment retrieval output to a local JSON file automatically, which creates persistent storage of potentially sensitive or regulated data without explicit user consent or a clear warning. On shared systems, CI runners, or managed agent environments, this can unintentionally expose collected comment data, request metadata, and operational details to other users or processes.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script writes the full output, including request details and retrieved results, to a local JSON file without explicit user consent or a visible disclosure before doing so. This can create unintended data persistence on shared systems or in sensitive environments, exposing scraped profile data and activity metadata to other local users or backup/sync processes.

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