Back to skill

Security audit

schema-markup

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with no AIG findings and one privacy-related caution about sending JSON-LD to external validation services; confidence is medium and coverage is partial.

Before installing, consider whether the JSON-LD you use could contain private or unpublished information. The scan says it may be sent to third-party validation services without a privacy warning. Skillspector scanned the single listed Markdown component but marked analysis partial because several local references could not be resolved, so the evidence is incomplete.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The validation workflow sends user-provided JSON-LD to third-party services without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill explicitly instructs submitting the final JSON-LD to Google's Rich Results Test and the Schema Markup Validator. That payload can contain user-supplied names, contact details and unpublished business information, but the skill does not warn that these values will be disclosed to external services.

Content

No source excerpt is available for this finding.