Security audit

红笔记数据收割

Security checks across malware telemetry and agentic risk

Overview

This skill coherently retrieves public Xiaohongshu data through a disclosed third-party API and saves results locally, with no evidence of hidden execution, account takeover, mutation, or exfiltration beyond its stated API use.

Install only if you are comfortable sending Xiaohongshu keywords or links to guaikei.com using your GUAIKEI_API_TOKEN. Review and delete the generated logs when they contain sensitive research, comments, profile data, or client work, especially on shared machines or systems with backup/log collection.

SkillSpector

By NVIDIA

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 (5)

Context-Inappropriate Capability

Medium

Confidence: 86% confidence
Finding: The CLI persists full search output to a local task log file, including the user’s keyword and all returned results, even though the stated purpose is simply to retrieve and present Xiaohongshu data. This creates unnecessary data retention and increases exposure of potentially sensitive queries or scraped content to other local users, backup systems, or later compromise of the host.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger text is very broad: it says to use the skill whenever a user mentions Xiaohongshu and wants to understand content, even if they did not explicitly ask for data or search. This can cause unintended invocation, leading the agent to send user-provided keywords or links to a third-party API when the user may have wanted general discussion, summarization, or advice instead.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The README states that all task results are automatically saved to a local `logs/` directory, but it does not clearly warn users that harvested Xiaohongshu note, comment, or profile data may persist on disk. Because this skill is specifically designed for bulk collection and analysis of third-party platform data, silent local retention increases the risk of unintended data exposure through shared machines, backups, log shipping, or accidental redistribution.

Missing User Warnings

Low

Confidence: 88% confidence
Finding: The CLI persists fetched comment results to a local JSON file derived from the target URL without any explicit warning, consent flow, or option to disable logging. Because comment data and metadata may contain personal or sensitive information, silent local retention increases the risk of unintended disclosure to other local users, backup systems, or later exfiltration from the host.

Missing User Warnings

Medium

Confidence: 82% confidence
Finding: The tool writes fetched results to a local JSON file automatically without obtaining user consent or clearly warning that scraped data will be persisted on disk. This can create unintended local data retention, exposing collected profile/post data to other local users, backups, or later compromise, especially in shared or automated environments.

VirusTotal

59/59 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:15