Security audit

Guaikei Kuaishou Data Harvester

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only Kuaishou public-data collection skill that uses a third-party API token and saves results locally, with those behaviors generally disclosed and aligned with its purpose.

Install only if you are comfortable sending Kuaishou keywords, URLs, request parameters, and your GUAIKEI_API_TOKEN to guaikei.com. Treat collected comments and creator data as public but still privacy-relevant, follow applicable platform/legal rules, and periodically clear the local logs directory if you do not want retained datasets.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (21)

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The package presents itself as a passive analytics and marketing research tool, but its declared CLI entry points also enable active platform interactions through posting and commenting. This mismatch can mislead users and reviewers about the skill’s real capabilities, increasing the risk of unauthorized automation, spam, or account actions being executed under the guise of data analysis.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The document explicitly describes tooling for bulk Kuaishou data collection, including keyword-based scraping, creator post harvesting, and comment extraction at scales up to 10,000 records, but provides no privacy, consent, legal, or platform-policy warning. In skill context, this omission makes operational misuse easier by normalizing mass collection of user-generated content and identifiers without safeguards, increasing the risk of privacy abuse and terms-of-service violations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This code sends a user-provided URL to remote API endpoints and uses an authentication token for those requests via postJson and getJson. While retry failures are logged, there is no confirmation prompt, user-facing disclosure, or explanatory comment/docstring in this file warning that external network transmission of input data and authenticated access will occur.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The CLI writes fetched comment data to a local JSON file automatically, but this file gives the user no explicit warning, consent prompt, or control over output location/retention. If comments contain personal data or sensitive content, this can create unintended local data exposure, especially on shared systems or when logs are harvested by other tooling.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The CLI writes the full task output to a local JSON file named from user-derived data without any clear prior disclosure or opt-in. Because the output may contain scraped results and request metadata, this can create unintended local data persistence, exposing sensitive or regulated data to other local users, backups, or later exfiltration.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This JavaScript file contains natural-language comments, error messages, and help text entirely in Chinese, including user-facing output such as thrown errors and --help content. Under the stated 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: Multiple user-visible error strings are hardcoded in Chinese, including credential and network error messages, with no indication that the skill is region-specific or that users can opt into a language. This is a natural-language locale policy concern because the skill effectively forces a specific language without documented choice or justification.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This code constructs and sends an outbound HTTPS POST request including a TOKEN header and JSON body, but the file provides no confirmation prompt, logging, comment, or docstring disclosing that user or system data will be transmitted off-host. For code files, outbound network transmission of potentially sensitive data should have some visible disclosure unless clearly documented elsewhere.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This code issues an outbound HTTPS GET request with a TOKEN header and query parameters, but there is no confirmation prompt, logging, comment, or docstring explaining that data is sent to an external service. That lacks the disclosure expected for network operations in code files when the transmission may include user or system data.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This JavaScript file contains multiple user-facing string literals in Chinese for validation errors. Because the skill does not offer a language/locale choice or document that it is intentionally China/Chinese-specific, it appears to force a specific language without user opt-in, 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: 82% confidence
Finding: The package description and keywords are entirely in Chinese and specifically target the Kuaishou platform, but the manifest provides no indication that this is an intentional locale-specific skill or that users can opt into another language. Under the policy for natural-language violations, forcing a specific language without opt-in can be a concern unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The error and status messages in this file are written only in Chinese, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language context. This can violate a language/locale policy when a skill forces a specific language without user opt-in.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The code sends the user-provided search keyword to a remote API via postJson and includes a token parameter, but this file contains no confirmation prompt, user-facing notice, or explanatory comment/docstring about that transmission. Because network calls that transmit user or system data fall under the warning requirement for code files, this is a missing-disclosure issue unless covered elsewhere in markdown documentation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The getJson call transmits the keyword, sorting/time filters, limit, and token to a remote endpoint, but the file provides no user-facing warning, confirmation, or explanatory comment about this network activity. For code files, remote transmission of user or system data should have some visible disclosure unless the behavior is explicitly documented elsewhere or is clearly the skill's stated purpose.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: No manifest is available, so there is no documented purpose or scope establishing that this skill should access credentials from the process environment. The code explicitly reads GUAIKEI_API_TOKEN, which is a capability beyond simple local argument processing and indicates authenticated external service use.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The CLI descriptions and messages are written in Chinese throughout the file, with no indication that another language is supported or that the locale is intentionally restricted. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The code emits all user-facing status and error messages in Chinese, such as the validation errors at L07 and L11, without offering a language choice or documenting that the skill is intended only for Chinese-speaking users. This is a natural-language locale policy concern because the file hardcodes a specific language for interaction.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The error path explicitly references the GUAIKEI_API_TOKEN environment variable, indicating this skill relies on sensitive credentials, but the file contains no disclosure or documentation warning that such credentials are required and used for remote requests. For code files, sensitive credential use should have some visible explanation unless clearly documented elsewhere.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The thrown error string is hard-coded in Chinese (重试${maxAttempts}次后失败). This imposes a specific language in user-visible output without offering locale selection or documenting that the skill is intended only for a Chinese-speaking context.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: This code accepts and uses a skill token sourced from an environment variable and only logs that a private token is being used. While it validates the token format, it does not clearly disclose to the user that a sensitive credential is being accessed and used by the skill, which is relevant under the missing user warnings criteria for code files.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This utility prints a Chinese module description and banner text directly to stderr, which imposes a specific language on users without any opt-in or locale selection. The policy explicitly flags language or locale constraints when the skill does not offer a choice or document a justified regional scope.
Content: No source excerpt is available for this finding.