Schema Markup Generator

Security checks across malware telemetry and agentic risk

Overview

This is a coherent SEO helper for generating Schema.org JSON-LD, with no evidence of hidden execution or data theft.

Safe to install for normal schema-markup work. Review any saved memory summaries before confirming them, and only let the skill fetch pages you intend the agent to analyze.

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 (3)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrase "JSON-LD" is broad enough to activate on ordinary technical discussion rather than an actual request to use this skill. This can cause incorrect skill routing, pulling in web-fetching and schema-generation behavior in contexts where the user only mentioned the term descriptively.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrase "schema.org" is a common reference term and may appear in educational, debugging, or comparative discussions without any intent to invoke this skill. Overbroad activation increases the chance of unintended execution and cross-skill misrouting, especially in general SEO or web-development conversations.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The phrase "rich snippets" is ambiguous and widely used in general SEO discussion, so it can match analysis or strategy conversations rather than a request for schema generation. This broad trigger may cause the agent to invoke the skill in the wrong context and produce misleading or unsolicited output.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal