skills/builderio/agent-native/content/Gen Agent Trust Hub

content

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation references the installation of @agent-native/core via npx. This is a standard setup procedure for the associated development environment.
  • [COMMAND_EXECUTION]: The skill utilizes pnpm action to perform document management tasks such as list-documents, get-document, and edit-document. These operations are limited to the scope of content authoring and repository management.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads and processes repository-backed Markdown and MDX files.
  • Ingestion points: Markdown and MDX files located in docs/, blog/, content/, and resources/ folders accessed via pull-document or get-document tools.
  • Boundary markers: The skill does not define specific delimiters or instructions to treat ingested document content as untrusted data.
  • Capability inventory: The skill can modify the local filesystem through edit-document, update-document, and write-local-component-file actions.
  • Sanitization: No explicit validation or filtering of document content is described prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 07:51 AM
Security Audit — agent-trust-hub — content