ClawHub

schema-markup

Security checks across malware telemetry and agentic risk

Overview

This skill is a focused schema-markup helper with a local validator and no evidence of hidden, destructive, or unrelated behavior.

Safe to install for structured-data work. Only run the validator on HTML you intend to analyze, and keep marketing-context.md free of secrets because the skill may read it to tailor recommendations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
83% confidence
Finding
The skill instructs the agent to read `marketing-context.md` automatically before asking questions, without telling the user that local project data may be accessed. This creates a privacy and consent issue because potentially sensitive business context could be ingested unexpectedly, even though the file scope appears narrow and relevant to the skill's purpose.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal