Security audit

guaikei·小红书达人评估数据

Security checks across malware telemetry and agentic risk

Overview

The skill largely does what it claims, but it handles an API token in URL query strings and automatically saves fetched social-media data locally.

Install only if you are comfortable sending Xiaohongshu keywords, URLs, and collected public content through the Guaikei API and keeping full results in local log files. Protect the GUAIKEI_API_TOKEN as a paid or private credential, and avoid using this skill for sensitive tracking targets or data you do not want retained locally.

SkillSpector

By NVIDIA

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 (4)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The activation text is intentionally broad: it says the skill should be used even when the user did not explicitly say 'collect' or 'scrape,' as long as the task involves obtaining Xiaohongshu content data. That can cause over-triggering of a data-collection skill and lead to unintended scraping, unnecessary third-party data transfer, or collection beyond the user's informed intent.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The documentation instructs users to configure an external service API token and pass user-supplied keywords, note URLs, profile URLs, and potentially retrieved content through the skill, but it does not clearly disclose that this data will be transmitted to a third-party service. This creates a privacy and data-governance risk because users may unknowingly send sensitive research targets, tracking targets, or collected social-media content outside their expected trust boundary.

Missing User Warnings

High

Confidence: 96% confidence
Finding: The API token is placed in GET query parameters when calling /api/xiaohongshu/comment/info. Query strings are commonly exposed in browser history, intermediary logs, reverse proxies, monitoring systems, and referrer data, which can leak the credential and allow unauthorized API access if captured.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The CLI writes the full search output to a local JSON file automatically, and the data may include scraped platform content or metadata the user may not expect to be persisted on disk. In a data-collection skill context, silent persistence increases the risk of accidental retention, local disclosure, or mishandling of collected third-party data, especially on shared machines or ephemeral automation runners.

VirusTotal

64/64 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:16