Security audit

Kuaishou Guaikei Dashi

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Kuaishou public-data lookup tool, with the main caution that fetched results are saved locally by default.

Before installing, confirm you are comfortable sending Kuaishou keywords, URLs, and the GUAIKEI_API_TOKEN to the Guaikei API service. Review any platform terms and privacy obligations for scraping or storing public comments, and periodically delete or protect the local logs directory if results may contain sensitive business intelligence or personal data.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The package metadata markets the skill as a passive analytics and monitoring tool, but the declared entry points also enable active posting and commenting. This capability mismatch can mislead users and reviewers about the true behavior and permissions of the skill, increasing the risk of unauthorized social-platform actions, spam, or account misuse once installed or invoked.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The README states that all task results are automatically saved to the logs directory, but it does not clearly warn users that scraped platform data, comments, URLs, and analysis outputs will be persisted to local disk. This creates a real data-handling risk because operators may assume the tool is ephemeral, while local storage can expose sensitive business intelligence or regulated personal data through backups, shared machines, or later exfiltration.

Missing User Warnings

Medium

Confidence: 83% confidence
Finding: The script writes fetched comment data to a local JSON file by default, and that data may contain personal information, usernames, or other user-generated content. Silent persistence increases privacy and data-handling risk because sensitive scraped content can remain on disk longer than intended, be accessed by other local users/processes, or be unintentionally redistributed.

Missing User Warnings

Low

Confidence: 88% confidence
Finding: The CLI writes the full search output, including the user’s keyword and returned results, to a local file automatically at the end of execution without an explicit opt-in or a clear warning at the write site. This can expose potentially sensitive queries or scraped content to other local users, backups, logs, or later unintended reuse, especially on shared systems or CI environments.

VirusTotal

60/60 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