Security audit

Kuaishou Guaikei Dashi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Kuaishou public-data analysis tool that uses a third-party API and saves local result logs, with no evidence of hidden, destructive, or deceptive behavior.

Before installing, users should be comfortable sending Kuaishou keywords, URLs, and the Guaikei API token to the third-party guaikei.com service, and should periodically review or delete saved JSON files in the local logs directory if the queries or returned comments are sensitive.

A.I.G

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

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (22)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill clearly depends on a third-party API service and explicitly states that data is sent externally, but the warning is buried in later sections instead of being presented prominently before use. This creates a real transparency and privacy risk because user-supplied keywords, URLs, and fetched public-data targets may be transmitted off-platform without sufficiently explicit user awareness or consent at invocation time.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The code persists the full output, including requested URL and retrieved comments, via log.taskWrite. Although the script prints status messages for fetching, there is no visible user-facing disclosure in this file that results will also be saved to disk, and file writes are a safety-relevant operation under the rule.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: With no manifest available, the skill's purpose is unknown, so accessing process.env.GUAIKEI_API_TOKEN introduces a credential-handling capability that is not justified by any stated intent. This is a semantic capability expansion beyond simple local argument processing and output formatting.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The code invokes createPostTask and getPostTask using a token and URL, indicating interaction with an external service rather than purely local processing. Because no manifest or declared purpose is available, this networked data-retrieval capability is unjustified by stated intent.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The script saves the full output to disk via log.taskWrite(...), which is a file-write operation affecting user data handling. Although the script logs progress for network activity, this file does not disclose that results will be persisted locally before performing the write.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The script persists the full search output to a local JSON file automatically, using a filename derived from user input. Even though this is a CLI tool, silently writing potentially sensitive queries and returned content to disk can expose user activity to other local users, backups, log collectors, or later compromise. In this skill context, search keywords and results may reveal research interests or operational intent, which makes the behavior more privacy-sensitive than a purely transient command.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This JavaScript file contains natural-language comments, error messages, and help output exclusively in Chinese, including thrown errors and CLI help text. Per the policy, forcing a specific language without user opt-in is a locale/language policy violation unless the constraint is explicitly justified, which is not present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The code emits all user-facing status and error messages in Chinese, which imposes a specific language on users without any visible opt-in or documented locale limitation. This is a natural-language policy concern because the skill does not appear to offer alternative language handling or justify a Chinese-only interface.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The hardcoded error text is entirely in Chinese and directs users to contact a specific WeChat number, which assumes a language and locale without offering any choice. This is a natural-language policy issue because the skill does not provide language opt-in or an alternative localized message.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: This code sends JSON payloads and a TOKEN header over HTTPS in both POST and GET helpers, which is a network operation that may transmit user or system data. There is no confirmation prompt, logging, comment, or docstring in this file disclosing that outbound requests and credential use occur.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The skill metadata and usage guidance are primarily written as Chinese-only invocation phrases such as '当用户要"搜快手视频 / 看快手博主作品 / 分析快手评论 / 做快手数据分析"时使用', while the file does not state that users may interact in other languages. This can be a locale-policy issue because it implicitly privileges one language without explicit opt-in or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This manifest is subject to natural-language policy checks, and the description text is presented only in Chinese. That can constitute a language/locale policy violation because the file does not indicate user opt-in, multilingual support, or a documented region-specific constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The natural-language content of the skill forces a single language presentation without any visible opt-in or alternative locale guidance. Under the stated policy, a skill should not impose a specific language unless it offers user choice or clearly documents a justified locale constraint.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file documents that all task results are automatically saved to logs/, which can affect user data handling and local privacy expectations. Although logging is mentioned, the README does not clearly warn users that fetched URLs, keywords, and analysis outputs will persist on disk unless managed or deleted.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The heading "快手guaikei运营大师" indicates a Chinese-only presentation, and this file provides no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rule for language/locale, forcing a specific language without opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The file’s headings, parameter descriptions, and examples are all presented only in Chinese. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale/language policy issue when no alternative or justification is provided.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: After producing output, the code derives a name from the URL and writes the full result JSON to a local file via log.taskWrite. When the skill's intended scope is undocumented, this local persistence is an additional capability not justified by any stated purpose.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This code creates directories and writes content to a log file on disk, which is a safety-relevant file write operation. Although it prints a success message after the write completes, there is no prior warning, confirmation, or explanatory comment/docstring disclosing that user-provided content will be persisted under the logs directory.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The thrown fallback error string is hard-coded in Chinese (重试${maxAttempts}次后失败). For a general-purpose utility file, this imposes a specific language on users without offering localization, opt-in, or documentation that the skill is region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This file contains user-facing warning and info strings only in Chinese, which imposes a specific language on users without any opt-in or indication that the skill is intentionally region-specific. That matches the natural-language policy concern for forced language/locale behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The file contains user-facing Chinese text in the module comment and banner output, including the visible terminal banner string. If organizational policy requires offering language or locale choice, this hard-coded language selection can be a natural-language policy issue because no opt-in or configurability is provided.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This code emits all validation and error messages in Chinese only, such as at L05, L10, L14, L18, L23, and throughout option validation. Under the policy, forcing a specific language without user opt-in or documented justification is a natural-language policy violation.
Content: No source excerpt is available for this finding.