Security audit

kuai-shou-trend-insights

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Kuaishou public-data lookup tool that uses a third-party API token and saves results locally.

Install only if you are comfortable sending Kuaishou search terms, creator/video URLs, limits, and your GUAIKEI_API_TOKEN to guaikei.com. The retrieved public results, including comments and account/video metadata, are saved locally under logs, so avoid using the skill with sensitive research targets unless that local record is acceptable.

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 (31)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The declared description promises Kuaishou-specific public data retrieval and analysis capabilities. However, the provided code chunk is an unrelated utility module for command-line argument parsing. It does not access Kuaishou, perform scraping or API requests, retrieve videos/posts/comments, or generate analysis outputs. This is a material description-behavior mismatch, not merely a supporting detail, because the actual code shown lacks the core advertised functionality.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The declared purpose is a Kuaishou public-data retrieval and analysis skill. However, the supplied code chunk only implements a helper for writing log content to local files. It uses the filesystem (`fs`), path handling, filename sanitization, directory creation, and file writing. There is no network access, no Kuaishou API interaction, no scraping, no structured data extraction, and no analysis logic. Because the code’s primary behavior is unrelated to the declared end-user functionality, this is a clear description-behavior mismatch rather than a mere supporting detail.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: The declared purpose describes a network/data-collection skill focused on Kuaishou content retrieval and analysis. However, the supplied code chunk contains only a utility function that reads package.json from the local filesystem and returns the package name. This is materially unrelated to the declared primary purpose and shows none of the stated capabilities such as searching videos, scraping creator works, or fetching comments. While this could be a supporting utility within a larger skill, based on the supplied code chunk alone the behavior does not accurately represent 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

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: 93% confidence
Finding: This file presents all user-facing instructions, parameter descriptions, and examples only in Chinese. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not present here.

Context-Inappropriate Capability

Medium

Confidence: 80% confidence
Finding: The manifest describes a skill for retrieving public Kuaishou data such as videos, creator posts, and comments. This CLI additionally depends on a secret environment token (`GUAIKEI_API_TOKEN`) to operate, which introduces credential handling and reliance on a separate service capability that is not stated in the skill purpose.

Missing User Warnings

Medium

Confidence: 81% confidence
Finding: The calls to createCommentTask and getCommentTask send the user-supplied video URL and limit, along with an API token, to an external service. This file lacks a clear user-facing warning or help text stating that input data will be sent over the network.

Description-Behavior Mismatch

Medium

Confidence: 89% confidence
Finding: The manifest frames the skill as searching and fetching public Kuaishou data and outputting structured results for analysis. In addition to returning JSON on stdout, the code derives a filename from the URL and writes the full result set to disk via `log.taskWrite`, adding local data persistence not described in the manifest.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The code writes the full output, including request details and retrieved comments, to a file via log.taskWrite. Although the CLI prints progress messages, there is no user-facing disclosure here that data will be persisted locally, and file writes are safety-relevant operations under this rule.

Context-Inappropriate Capability

Medium

Confidence: 89% confidence
Finding: The manifest describes a skill for searching Kuaishou public data, listing creator posts, and fetching comments. This CLI additionally depends on a secret token from process.env (GUAIKEI_API_TOKEN), which introduces credential access beyond the stated public-data retrieval purpose and is not mentioned in the manifest.

Description-Behavior Mismatch

Medium

Confidence: 86% confidence
Finding: The manifest frames the skill as a data retrieval and analysis tool that outputs structured data for insights use cases. This file also writes the full output to disk via log.taskWrite, which is a side effect not evident from the description and goes beyond simple retrieval/output behavior.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: This code persists the full command output to disk via log.taskWrite, which is a file-write operation covered by the missing-warning rule for code files. Although the script prints status messages, it does not clearly disclose to the user that a local file will be created containing the request details and results.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: This code includes natural-language strings in Chinese for errors, warnings, and help output, starting with the file header and continuing throughout the parser and help generator. Under the policy, forcing a specific language without user opt-in or justification is a locale/language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: This code emits user-facing status and error messages only in Chinese, such as the validation errors on these lines. For a general utility file, that imposes a specific language without any visible opt-in or documented region-specific justification, which matches the locale-policy concern in SQP-3.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: This code sends request parameters/body data to a remote host and includes a TOKEN header, which is a safety-relevant network operation under the audit criteria. There is no confirmation prompt, logging, comment, or docstring in this file disclosing that user/system data and credentials may be transmitted.

Missing User Warnings

Medium

Confidence: 81% confidence
Finding: The token parameter is validated and then inserted into the HTTP headers as TOKEN, which constitutes use of sensitive credentials. Under the rule, credential access/use should not be silent when there is no accompanying warning, comment, or documented disclosure.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: The package description is written entirely in Chinese, which can impose a specific language on users without any visible opt-in or explanation that the skill is intended only for a Chinese-speaking or region-specific audience. Under the language/locale policy, this is a natural-language policy concern because the metadata does not offer alternatives or justify the locale restriction.

VirusTotal

63/63 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