Security audit

Guaikei Kuaishou Trending Video Fetcher

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Kuaishou public-data collection skill that uses a GUAIKEI API token, sends queries to a third-party API, and saves fetched results locally.

Install only if you are comfortable sending Kuaishou keywords, profile/video URLs, and your GUAIKEI API token to guaikei.com. Treat saved logs as potentially sensitive public-data exports, keep the token private, and avoid committing or sharing the logs/ directory.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (22)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest description is primarily written in Chinese and the rest of the skill documentation continues in Chinese, with no indication that users may interact in another language or choose a preferred locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The README states that all task results are automatically saved to a logs/ directory, but it does not warn users that those results may contain scraped profile URLs, comments, keywords, or other potentially sensitive business or personal data. In a data-collection tool, silent persistence increases the risk of unintended local exposure, over-retention, accidental sharing, or inclusion in backups and source control.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: No manifest is available to justify the skill's operational scope, so environment-based credential access cannot be tied to an explicitly stated purpose. The code pulls GUAIKEI_API_TOKEN from process.env and uses it to drive external comment-retrieval operations, which is a privileged capability beyond simple local CLI argument handling.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The code reads GUAIKEI_API_TOKEN from the environment and then invokes external API functions to create and fetch comment tasks. While this network behavior is part of the apparent purpose of the tool, this file does not visibly disclose that user-provided URLs and authentication data will be used in remote API requests.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file does more than local parsing or formatting: it creates a remote task and then polls or retrieves results through the comment API. With no manifest available, this network-backed data collection capability is unjustified by any declared skill purpose and should be treated as context-inappropriate until explicitly documented.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The script writes retrieved comment data to a local JSON file without explicit user consent or a clear warning in the interface. If comments contain personal data or sensitive content, this can create unintended local data retention and privacy exposure, especially on shared systems or automated environments.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The script writes the full output, including request details and fetched results, to a local JSON file without explicit user consent or prominent disclosure. This can expose potentially sensitive scraped data to other local users, backup systems, CI artifacts, or shared workspaces, especially because the filename is partly derived from user-controlled input.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This file contains natural-language comments and CLI output such as errors, usage text, and help messages entirely in Chinese. Because the skill does not provide user opt-in, locale selection, or justification that it is intended only for a Chinese-speaking context, it violates the language/locale policy criterion.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The helper sends request parameters/body and a TOKEN header to a remote host via HTTPS in both POST and GET flows. In this file there is no confirmation prompt, logging/print statement, or comment/docstring disclosing that user/system data and credentials are transmitted over the network.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This code emits user-facing warning and info strings only in Chinese, which effectively forces a specific language on users. The file does not provide any opt-in, localization mechanism, or justification for a Chinese-only locale, which matches the language/locale policy violation criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This code emits multiple user-facing error strings only in Chinese, which forces a specific language on users without any opt-in or alternative locale handling. The stated policy flags language/locale constraints when they are imposed without user choice or clear justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The package description is written entirely in Chinese, which imposes a language choice in user-facing metadata without offering an alternative language or opt-in. Under the policy, forcing a specific language without user choice is 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: 72% confidence
Finding: SQP-3 applies to all file types and includes language or locale policy violations. The documentation is entirely in Chinese and does not indicate that the skill supports other languages, offers user choice, or is intentionally restricted to a Chinese-speaking audience for a documented regional reason.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown file presents all user-facing instructions and examples only in Chinese. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue when no alternative or explicit justification is provided.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This code sends the supplied url and token to a remote API via postJson, which is a data-transmitting network operation covered by the warning requirement for code files. The file includes retry error logging, but no confirmation, user-facing notice, or explanatory comment/docstring disclosing that user data and auth credentials are sent to an external endpoint.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The getJson call transmits the provided url, limit, and token to a remote endpoint, which is a network operation involving user or system data. While retry failures are logged, there is no user-facing warning, confirmation, or inline documentation in this file explaining that these values are sent off-box.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: After retrieving results, the script writes a JSON file containing the request and comment data to local storage. In the absence of a manifest, this data persistence is an additional capability not justified by any stated purpose and may exceed what a user expects from a comment-fetching CLI.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The code persists the full search output to disk via log.taskWrite(...), which is a file write operation covered by the missing-warning rule for code files. Although the CLI prints status messages and help text mentions token configuration, there is no visible disclosure here that search inputs/results will be saved locally.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The code emits user-facing status and error messages in Chinese only, such as the validation errors on these lines. That creates a language/locale policy issue if the skill is expected to be generally usable, because no user opt-in or alternative locale is offered.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Multiple thrown error strings are written only in Chinese, including parse, timeout, network, and validation errors. This enforces a specific language for user-visible behavior without any opt-in or locale selection, which violates the language/locale policy criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The thrown error string is hard-coded in Chinese (重试${maxAttempts}次后失败). This imposes a specific language on users and downstream logs without any indication of locale selection or justification, which matches the natural-language policy violation criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The module’s comment and banner text are written in Chinese, and the banner shown to users is hard-coded as Chinese-language output. This imposes a specific language on users without any opt-in or documented locale constraint, which matches the language/locale policy violation criteria.
Content: No source excerpt is available for this finding.