Security audit

公域流量精准获客与竞品截流系统

Security checks for vulnerabilities and agentic risk

Overview

This skill openly performs Douyin lead mining, but its bulk collection, off-host API use, and automatic local storage of user/comment data need careful review before installation.

Review before installing. Use only if you are authorized to collect and process the targeted Douyin public data, and check platform terms, privacy obligations, and anti-spam rules. Expect your API token and search/video/account inputs to be sent to guaikei.com, and expect result logs containing user IDs, nicknames, comment text, and related metadata to remain on disk until you delete or secure them.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (7)

Context-Inappropriate Capability

Low

Confidence: 94% confidence
Finding: The authentication error path includes an unrelated personal contact/upsell message ('联系微信...获取解决方案') rather than a neutral security or support response. In a credential failure path, this can socially steer operators toward an unverified off-platform contact, creating trust-manipulation and potential phishing/social-engineering risk, especially in a data-harvesting marketing tool.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly states that comment, search, and account-derived lead data are automatically saved into a local `logs` directory, but it does not provide a meaningful privacy and data-retention warning. Because the tool is designed for lead mining from public comments and competitor traffic interception, those log files may contain identifiers, URLs, inferred interests, and other potentially sensitive commercial or personal data that can be exposed to other local users, backups, or downstream systems.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The README explicitly promotes monitoring competitor comment sections and converting competitor fans into customers, while omitting any warning about privacy expectations, platform terms, scraping restrictions, or account-enforcement risk. In a lead-generation skill, this normalizes potentially non-compliant targeting behavior and can encourage misuse of user-generated data for unsolicited outreach or policy-violating customer acquisition.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The documentation explicitly enables bulk collection of Douyin user works and comment data at scale, but provides no privacy, consent, retention, or lawful-use guidance. In the context of a customer-acquisition tool focused on competitor interception, lead screening, sentiment conversion, and private-traffic redirection, this omission materially increases the risk of profiling individuals, scraping personal data, and using public interactions for unsolicited outreach.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The CLI writes retrieved comment data to a local JSON file automatically, with no explicit consent prompt or warning in this entrypoint. Because this skill is designed for lead mining and comment scraping, the output may contain personal data or sensitive business intelligence, creating privacy and data-handling risk if users are unaware that data is being persisted on disk.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The script sends the provided URL and query parameters to remote API functions without clearly informing the user at the point of use that their input will be transmitted off-host. In a data-extraction skill focused on public-comment mining and customer acquisition, undisclosed outbound transmission can create privacy, compliance, and trust issues, especially if operators assume the tool is purely local.

Missing User Warnings

Low

Confidence: 88% confidence
Finding: The CLI writes the full search output to a local JSON file whose name includes the user keyword, and the tool context is customer acquisition based on comment/data mining, so results may contain sensitive business intelligence, personal data, or targeting information. Persisting that data locally without an explicit warning, opt-in, or retention control increases the risk of unintended disclosure through shared machines, backups, or insecure log directories.

Static analysis

No suspicious patterns detected.