Back to skill

Security audit

小红书趋势洞察

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only Xiaohongshu trend-research helper that uses a SocialDataX API key, with one privacy note around sharing full returned XHS URLs.

Install only if you are comfortable using SocialDataX for XHS research with your SOCIALDATAX_API_KEY. Treat full XHS links returned by the tool as potentially share-sensitive, especially when exporting reports or forwarding results outside your workspace.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Ssd 3

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs the agent to preserve and reproduce full `note_url` values including `xsec_token`, and to avoid truncating, redacting, or reconstructing them. If those URLs or tokens are access-bearing, user-scoped, time-limited, or otherwise sensitive, this behavior can leak secrets into model outputs, logs, chat transcripts, downstream tools, or shared reports. In a trend-analysis skill, full tokenized URLs are usually not necessary for high-level analysis, so the instruction increases exposure without a strong security justification.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.