Security audit

guaikei-xhs-find-notes

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu public-data retrieval tool that calls a third-party API and locally saves results, with no evidence of hidden access, posting, or destructive behavior.

Install this only if you are comfortable sending Xiaohongshu keywords or links and your GUAIKEI_API_TOKEN to guaikei.com. Review and clean the local logs directory as needed, since fetched notes, comments, account data, and analysis-ready JSON results are saved there automatically.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (4)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The description allows activation even when the user does not explicitly say 'Xiaohongshu', including broad aliases and link patterns. Overly broad routing can cause the agent to invoke this skill on ambiguous requests, leading to unnecessary external data disclosure to a third-party API and incorrect task handling.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger rules include broad task categories such as trend research, KOL selection, and content analysis without sufficiently strict scope checks. In practice this can make the agent over-trigger the skill for generic marketing or analysis requests, sending user-supplied text or links to the third-party provider when the user did not clearly intend that integration.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The README states that all task results are automatically saved to a local `logs/` directory, but it does not clearly warn users about retention, sensitivity, or cleanup. Because this skill collects structured note, comment, and account data at scale, saved logs may accumulate third-party content and analysis artifacts that could later be exposed, shared, or mishandled.

Missing User Warnings

Medium

Confidence: 73% confidence
Finding: The tool persists fetched comment data to a local file without an explicit warning or consent flow in this file. Because comment content may contain personal or sensitive data and filenames are derived from the target URL, this can create unintended local data retention and privacy exposure on shared systems.

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