Schema Markup

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only SEO schema helper with no executable code or hidden high-risk behavior.

Safe to install for Schema.org and JSON-LD assistance. Be aware it may activate on broad schema-related wording, and avoid storing secrets in project-context files because the skill may ask the agent to read them for site context.

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: 85% confidence
Finding: The trigger list is very broad and includes highly generic terms such as "schema," "structured data," and many common SEO phrases, which can cause the skill to activate for requests that do not actually require this specialized behavior. Over-broad invocation increases the chance of misrouting user requests, unnecessary exposure to the skill's instructions, and unintended tool or workflow usage in larger agent systems.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal