Security audit

guaikei-douyin-content-index

Security checks for vulnerabilities and agentic risk

Overview

This skill mostly does what it says, but its broad auto-activation rules and contradictory runtime token-error behavior need review before installation.

Install only if you intend to send Douyin public-data queries and URLs to guaikei.com using a GUAIKEI_API_TOKEN. Narrow or confirm ambiguous requests before invoking it, and periodically review or delete the generated logs because they can contain scraped public comments, account data, and business research results.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill says it should be used even when the user does not mention '抖音', which makes activation criteria too broad for a tool that performs external data collection and uses an API token. Overbroad triggering can cause the agent to invoke the skill in unrelated contexts, sending unintended queries or URLs to the external service and producing actions the user did not clearly authorize.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: Trigger phrases like '热搜/热点/榜单/搜索/评论/作品/主页/账号/博主' are common, cross-platform terms and are not sufficiently tied to Douyin. In an agent environment, these generic phrases can misroute ordinary user requests into this skill, causing unintended third-party requests, token usage, and incorrect handling of content from other platforms.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The README presents quick-start commands that scrape Douyin data but does not clearly warn, at the point of use, that running them will export collected data and persist JSON logs locally. This can cause users to unknowingly retain potentially sensitive scraped content on disk, increasing privacy, compliance, and data-handling risk, especially in shared or managed environments.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The CLI persists fetched comment data to a local JSON file by default, which can unintentionally store potentially sensitive or regulated user-generated content on disk without explicit user consent, warning, retention controls, or access protections. In this skill’s context, the data is public Douyin comment content rather than private account data, so the severity is moderated, but silent local persistence still increases privacy, compliance, and data-leak risk on shared systems or CI environments.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The CLI persists fetched Douyin post results to a local JSON file automatically, without any user consent, opt-out, or visibility control in this code path. Because the skill is designed for bulk public-data collection and analysis, the saved output can accumulate sensitive business intelligence, scraped content, or potentially personal data from public profiles on disk where other local users, backups, or downstream processes may access it unexpectedly.

Static analysis

No suspicious patterns detected.