umbraco-tiptap-toolbar-extension

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill is designed to ingest data from external documentation via the WebFetch tool.
  • Ingestion points: The workflow explicitly directs the agent to fetch content from docs.umbraco.com and tiptap.dev.
  • Boundary markers: While explicit boundary markers are not used in the workflow description, the targeting of specific, high-trust vendor documentation sites minimizes the risk of adversarial content.
  • Capability inventory: The skill possesses Read, Write, Edit, and WebFetch capabilities, allowing it to read external data and modify the local filesystem.
  • Sanitization: No explicit sanitization is performed, but the primary use case (fetching official docs for code generation) is a low-risk activity within this context.
  • Data Exposure & Exfiltration (SAFE): No hardcoded credentials or access to sensitive system paths (e.g., SSH keys, env files) were found. Network activity is limited to fetching documentation from trusted domains.
  • Unverifiable Dependencies (SAFE): The code templates reference standard industry packages (@umbraco-cms/backoffice and @tiptap/core) and do not attempt to install or execute untrusted third-party code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:58 PM