AI News Infographics

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is aligned with creating shareable AI-news infographics, though users should remember the generated image may be uploaded externally.

Install only if you are comfortable with generated infographic images being saved and potentially uploaded to a CDN for sharing. Use it for public AI-news content, review facts before posting, and avoid including confidential prompts, proprietary details, or internal context in images you do not want externally accessible.

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to save generated files to the workspace and upload them to a CDN without explicit user consent or notice. This creates a real data-handling risk: generated content, prompts, embedded links, or user-provided material could be externally shared unexpectedly, causing privacy leakage or unauthorized publication.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal