shader

Security checks across malware telemetry and agentic risk

Overview

This shader helper is coherent and limited to ordinary shader-writing guidance, templates, and local demo helpers.

Reasonable to install for shader prototyping. Treat the included demos like normal development templates: review npm dependencies before use, avoid elevated privileges, and keep the Vite dev server local unless you intentionally want network access.

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 allows implicit invocation, but the manifest does not define clear trigger constraints, exclusions, or scope boundaries. That can cause the agent to auto-select this skill in loosely related contexts, increasing the chance of unintended code generation or advice being applied where shader-specific behavior was not requested, which expands the attack surface for prompt-routing mistakes or misuse.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal