guaikei-douyin-get-creator-posts

• Outcome: Pass
• Latest audit: Aug 20, 2026 · 3:08 AM UTC
• Version: 1.0.0

Overview

This appears to be a legitimate Douyin public-data lookup skill, with clear notes that it uses a Guaikei API token, contacts an external API, and saves results locally.

Install only if you are comfortable sending Douyin search terms, profile or video URLs, and your GUAIKEI_API_TOKEN to guaikei.com. Keep the token private, rotate it if exposed, and review or delete the local logs directory when results include comments, usernames, or other data you should not retain or share.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 84% confidence
• Finding: The skill declares use of an environment variable token (`GUAIKEI_API_TOKEN`) and command execution via Node.js, but no explicit permission declaration is present in the metadata. This creates a governance gap where reviewers or runtime policy may not clearly understand that the skill accesses secrets, increasing the risk of unintended secret exposure or over-trusting the skill's capabilities.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The description explicitly says the skill can trigger even when Douyin is not named, which broadens activation boundaries beyond clear user intent. Over-broad routing can cause the agent to invoke external data collection unexpectedly, sending user queries to this skill when the user did not specifically request Douyin-related analysis.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The implicit trigger examples such as competitor research, popular content, or recent hot topics are generic enough to match many unrelated requests. This increases the chance of accidental invocation and unnecessary transfer of user prompts into a scraping-oriented workflow, which is especially sensitive because the skill performs external lookups and token-backed API access.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: The README explicitly promotes automatic JSON log export of scraped Douyin data, including author, post, comment, and hot-topic data, but does not warn that these logs may contain personal data or user-generated content that requires careful storage, retention, and sharing controls. In this skill context, the risk is elevated because the tool is built for bulk collection and analysis of public social-media data, which makes accidental internal overexposure or improper redistribution more likely.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README instructs users to place the API token in an environment variable but does not provide an upfront warning about credential leakage through shell history, process listings, CI logs, screenshots, or copied terminal sessions. In this context, the skill depends on a paid/privileged external token, so weak secret-handling guidance can lead to token theft, unauthorized API use, and account abuse.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The CLI persists fetched comment data to a local JSON file automatically, and comment payloads can contain personal data, usernames, or other sensitive content. Writing this data to disk without explicit user notice or opt-in increases the risk of unintended retention, later disclosure through shared workspaces, backups, or other local users/processes.

Missing User Warnings

Medium

• Confidence: 74% confidence
• Finding: The script transmits the user-supplied target URL and query parameters to external comment APIs, but there is no explicit disclosure in this file that the requested target will be sent off-host. In a data-retrieval skill, silent network transmission can expose user interests, targets under investigation, or internal-only URLs if a user supplies them mistakenly.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The CLI persists the full fetched results to a local JSON file automatically, and those results may include creator/profile metadata or other scraped content that users may not realize is being stored on disk. In a skill that fetches social-media data, silent local retention increases privacy, compliance, and accidental disclosure risk if the host is shared, backed up, or later exfiltrated.

VirusTotal

63/63 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.