Security audit

guaikei-kuaishou-search-comment-creator-fetcher

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Kuaishou public-data research tool that saves fetched results locally, which users should understand but is consistent with its stated purpose.

Install only if you are comfortable sending Kuaishou search terms, profile/video URLs, requested limits, and your GUAIKEI_API_TOKEN to guaikei.com. Expect fetched public results, including comments and account/video metadata, to be saved locally under the skill's logs directory; delete those files when they are no longer needed and avoid using the data outside authorized or compliant research workflows.

A.I.G

By Tencent

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

By NVIDIA

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Description-Behavior Mismatch

Medium

Confidence: 87% confidence
Finding: The script persists the full fetched comment payload to a local JSON file after completing the request. Comment data can contain personal or sensitive user-generated content, and silently storing it increases data retention and local exposure risk beyond transient fetch-and-display behavior.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The README states that all task results are automatically saved to a `logs/` directory, but it does not warn users that collected comment, account, or trend data may persist on disk and remain accessible to other local users, backups, or later processes. In this skill's context, the saved data can include scraped public content at scale, which increases the risk of unintended retention, redistribution, or exposure even if the source data is public.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The tool writes fetched comments to a local file without explicit user warning in this file, creating a privacy and data-handling issue. Users may reasonably expect a fetch utility to print results only, not retain a local archive of third-party content that could later be accessed by other local users or processes.

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