Security audit

kuaishou-detail

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Kuaishou public-data CLI integration that sends user-provided search terms or Kuaishou URLs to a third-party API and saves results locally.

Before installing, confirm you are comfortable sending Kuaishou keywords, video/profile URLs, and your GUAIKEI_API_TOKEN to guaikei.com, and periodically review or delete local logs if the collected public comments or URLs are sensitive to your workflow.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection

Findings (36)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The declared description promises a Kuaishou public-data retrieval and competitor-analysis skill. However, the supplied code chunk only implements reusable command-line argument parsing utilities (`parseArgs`, `readValueAfterFlag`, `buildHelp`). This is not merely a supporting implementation detail for the declared functionality because, in the provided chunk, there is no evidence of any actual Kuaishou-specific logic, network access, scraping, structured data extraction, or analytics. The code’s primary observable behavior is unrelated infrastructure for parsing CLI options, so the description does not accurately represent what this code chunk actually does.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: Yes, this is a mismatch. The declared purpose is centered on Kuaishou public data collection and analysis workflows, but the supplied code chunk only implements a generic log-writing helper using fs/path. It writes arbitrary provided content to local disk and does not show any network access, Kuaishou API interaction, scraping, structured data extraction, or analysis logic related to videos, creators, or comments. While logging can be a supporting detail in a larger skill, this specific chunk’s actual behavior is unrelated to the declared primary purpose and exposes an undeclared capability: local filesystem writes.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The declared purpose describes a network/data-collection skill focused on Kuaishou public content and analytics. The supplied code does not implement any of those behaviors; it merely reads a local package.json file to obtain the package name. This is a materially different purpose and accesses a local resource unrelated to the stated Kuaishou retrieval functionality. While this may be a utility helper, based on the provided chunk alone it does not match the declared description.

Ae1

High

Category: analysis-evasion
Content: | 查某个关键词的快手视频 | `scripts/kuaishou/search-cli.js` | `keyword` | 视频列表、作者信息、互动信息、跳转链接 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 查某个关键词的快手视频 | `scripts/kuaishou/search-cli.js` | `keyword` | 视频列表、作者信息、互动信息、跳转链接 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 看某个快手博主最近发布了什么 | `scripts/kuaishou/post-cli.js` | 博主主页 URL / user_id | 博主公开作品列表 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 看某个快手博主最近发布了什么 | `scripts/kuaishou/post-cli.js` | 博主主页 URL / user_id | 博主公开作品列表 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 看某个快手博主最近发布了什么 | `scripts/kuaishou/post-cli.js` | 博主主页 URL / user_id | 博主公开作品列表 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 看某篇快手视频的评论数据 | `scripts/kuaishou/comment-cli.js` | 视频 URL | 该视频的评论内容、评论者信息、互动数据 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 看某篇快手视频的评论数据 | `scripts/kuaishou/comment-cli.js` | 视频 URL | 该视频的评论内容、评论者信息、互动数据 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 看某篇快手视频的评论数据 | `scripts/kuaishou/comment-cli.js` | 视频 URL | 该视频的评论内容、评论者信息、互动数据 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: **👉 详细选项说明**, 可参阅 [完整选项说明](references/options.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: **👉 详细选项说明**, 可参阅 [完整选项说明](references/options.md)
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: - 更新记录：见 `references/changelog.md`
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Lp3

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The markdown instructions, headings, and operational guidance are predominantly in Chinese, which can impose a specific language on users or downstream agents. The policy allows locale constraints only when clearly documented and justified or when users are given a choice, neither of which is present here.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The package description is written entirely in Chinese and provides no indication that other languages are supported or that the user can choose a preferred language. This can violate language/locale policy when a skill implicitly requires a specific language without documented opt-in or justification.

Missing User Warnings

Medium

Confidence: 85% confidence
Finding: This markdown file documents a data-collection skill and states that all task results are automatically saved to `logs/`, which affects user data handling and local system state. While logging is mentioned, there is no explicit user warning about the persistence of potentially sensitive keywords, links, or collected output before use.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The script sends user-supplied input and an access token to createCommentTask/getCommentTask, which are network-facing by context, but this file provides no explicit disclosure that the command will contact a remote service using that data. For a data-fetching CLI, some networking is expected, yet the absence of any warning about transmitting the URL and token still leaves users uninformed.

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The manifest describes searching Kuaishou public data and outputting structured data for analysis, which implies retrieval and return of results. This CLI additionally writes the full output, including fetched comments, to a local JSON file via log.taskWrite, which is a side effect not stated in the skill description.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The code persists the full output, including request metadata and fetched comments, via log.taskWrite(). Although the CLI prints progress messages, there is no explicit disclosure here that running the command will save data to disk, which is a safety-relevant file write operation.

Context-Inappropriate Capability

Medium

Confidence: 91% confidence
Finding: The manifest describes searching Kuaishou public data and returning structured results for analysis. This file additionally persists the full output to a local file via log.taskWrite, which is not necessary to fulfill a read/query skill's stated purpose and introduces an extra data-retention capability.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: This code sends outbound HTTPS requests and includes a TOKEN header plus JSON/query data, which can transmit user or system data off-host. Within this file there is no confirmation prompt, user-facing log/print, or explanatory comment/docstring disclosing that network transmission occurs.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: This code emits validation errors only in Chinese via multiple string literals, with no indication that users can choose another language or that the skill is intentionally region-specific. That creates a natural-language policy issue because the skill effectively enforces a locale on all users.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: The natural-language instructions throughout the file are entirely in Chinese, which can amount to a language-policy issue if the organization expects skills not to force a specific language without user opt-in. The README does not indicate that Chinese is optional, user-selected, or required for a documented region-specific purpose.

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