ClawHub
Back to skill

Security audit

Hackernews Cn

Security checks across malware telemetry and agentic risk

Overview

This Hacker News skill is low risk: it has broad trigger words and appears to return mock HN data, but it does not request sensitive access or perform hidden actions.

Install only if you are comfortable with broad HN/startup-related activation terms. Treat the output as demo or sample data unless the skill is updated to clearly fetch live Hacker News or Algolia data.

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 trigger set includes very broad terms like "HN", "YC", and "创业", which can appear in many ordinary conversations unrelated to explicit invocation of this skill. That can cause unintended routing or activation, leading the agent to fetch external content or change behavior when the user did not clearly request Hacker News monitoring.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal