Juejin

Security checks across malware telemetry and agentic risk

Overview

This is a small instruction-only skill for summarizing public Juejin content, with no code, credential access, persistence, or hidden authority.

Reasonable to install for public Juejin article discovery and summaries. Users should keep it to public pages, avoid login-only or private content, respect Juejin rate limits and platform rules, and not use it for API bypass or bulk collection.

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 (1)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description is broadly phrased as applying whenever access or automation of Juejin-related content is needed, which can cause over-triggering on generic requests. An overly broad invocation rule can route unrelated user tasks into this skill, expanding the agent's access to external content and increasing the chance of unintended browsing or data collection behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal