guaikei-xhs-competitor-watch

• Outcome: Review
• Latest audit: Aug 12, 2026 · 3:18 AM UTC
• Version: 1.0.0

Overview

This skill is a purpose-aligned Xiaohongshu public-data retrieval tool, but users should understand that it sends inputs to guaikei.com and saves retrieved results locally.

Install only if you are comfortable sending Xiaohongshu keywords or links to guaikei.com using your GUAIKEI_API_TOKEN. Review and delete the logs/ directory if retrieved comments, profile data, competitor targets, or analysis outputs should not remain on disk.

SkillSpector

By NVIDIA

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 (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 85% confidence
• Finding: The skill requires access to the GUAIKEI_API_TOKEN environment variable but does not declare permissions explicitly, creating a mismatch between advertised and actual capabilities. This can weaken user awareness and review controls around secret access, especially because the skill also routes data to an external API service.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The description says the skill should be used whenever a task involves obtaining Xiaohongshu data, even if the user did not explicitly ask to collect or scrape it. That broad trigger increases the chance of unanticipated activation and silent transmission of user-supplied keywords or links to the third-party service, reducing meaningful user consent.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill's main usage sections emphasize data retrieval and API-driven operation, but the warning that requests depend on a third-party API and may externalize URLs, keywords, and retrieved content appears later and is not prominent. This creates a transparency and privacy risk because users may provide targets or content without realizing their data is being sent off-platform.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The README states that all task results are automatically saved to the logs/ directory, but it does not warn users that searched keywords, queried URLs, note details, comments, and derived analysis outputs may persist on disk. In this skill’s context, the saved data can include commercially sensitive competitor-monitoring inputs and potentially personal data from public profiles/comments, increasing the risk of unintended retention, local disclosure, and mishandling.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The CLI writes the full comment task output, including scraped comment data, to a local JSON file by default after successful execution. Comment content can contain personal data, usernames, or other sensitive public-profile information, and silently persisting it increases the risk of unintended retention, local disclosure, or later exfiltration from the host environment.

VirusTotal

62/62 vendors flagged this skill as clean.

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:16