personalized-news-collector

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only personalized news skill that uses recent context and web news feeds in a way that matches its stated purpose.

Before installing, be comfortable with the agent using recent conversation or memory to infer news interests and contacting third-party news sources. Ask it to confirm inferred interests first or to use only specific sources if you want tighter control.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger description is broad enough to activate on generic requests about 'current news' or 'events happening around,' which can cause the skill to run in situations the user did not explicitly intend. Because the skill then infers interests from recent memory and conversation history, overbroad invocation increases the chance of unnecessary processing of contextual data and unintended external lookups.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs external network access to collect news from multiple sources, but it does not tell the user that outside services may be contacted or that inferred interests may influence those requests. In a personalized context, this creates a privacy and transparency risk because the system may fetch data from third-party sources based on user-derived interests without clear notice or consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal