Security audit

小红书赛道分析

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu research workflow with optional supervised public-data collection, but users should handle collected comments and third-party integrations carefully.

Install only if you intend to do Xiaohongshu category research. Before running the collector, confirm you are using an authorized account, keep collection small and rate-limited, avoid non-public data, remove nicknames or other personal identifiers from outputs, and review any optional external Agent-Reach or third-party API setup separately.

SkillSpector

By NVIDIA

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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

Findings (4)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The README explicitly describes collecting public notes, profiles, and comments via browser automation and third-party platforms, but it does not provide concrete privacy, consent, retention, or platform-terms compliance guardrails. Even when data is publicly visible, large-scale collection and structuring of user-generated content can create legal, privacy, and policy risk, especially if personal data or behavioral signals are retained or repurposed.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger list contains broad phrases like '做赛道分析' and '赛道研究' that can overlap with general research or strategy requests, causing the skill to activate outside its intended narrow use case. Over-broad activation can misroute user requests into a specialized workflow, leading to inappropriate data-collection guidance or analysis framing without the user explicitly asking for Xiaohongshu-specific track analysis.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The positive trigger set includes broad colloquial phrasing such as evaluating whether a blogger's content is suitable for seeding, which blurs the boundary between this skill's stated scope and adjacent capabilities like single-account analysis or campaign planning. In a routing or activation system, overly broad triggers can cause the wrong skill to activate on sensitive marketing, profiling, or decision-support requests, leading to scope bypass and unreliable downstream behavior.

Unpinned Dependencies

Low

Category: Supply Chain
Content: playwright>=1.44.0
Confidence: 95% confidence
Finding: The dependency is specified with a lower-bound only constraint (`playwright>=1.44.0`), which allows future major or minor releases to be installed without review. This can introduce supply-chain risk, unexpected breaking changes, or newly introduced vulnerable versions in non-reproducible builds, especially for automation tooling that interacts with browsers and external content.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.