3dgs Paper Reader

Security checks across malware telemetry and agentic risk

Overview

This is a focused paper-reading skill for 3DGS research, with no executable code, install commands, credential handling, persistence, or hidden high-impact behavior.

Safe to install for 3DGS paper summaries. Only provide local PDFs you are comfortable having the agent read, and verify numerical paper results against the source paper when accuracy matters.

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

Low
Confidence
87% confidence
Finding
The skill is broadly described as handling 3DGS/NeRF paper reading from arXiv, titles, or local PDFs, but it does not clearly state when it should or should not activate. In an agentic environment, vague invocation boundaries can cause over-triggering on general research or paper-related prompts, leading to unintended file access, network fetches, or tool use beyond user expectations.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal