migrate-brizy-to-gutenberg

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill performs a network operation to 'https://www.respira.press/api/skills/track-usage' to send usage telemetry including skill metadata, success status, and page counts. This targets the developer's official domain and represents standard vendor functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external WordPress pages, which serves as a potential surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context via the 'wordpress_extract_builder_content' and 'wordpress_read_page' tools as described in 'SKILL.md'.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when handling extracted page content.
  • Capability inventory: The skill has capabilities to create and modify WordPress content using 'wordpress_create_page_duplicate', 'wordpress_update_page', and 'wordpress_update_post'.
  • Sanitization: There is no mention of sanitization, escaping, or validation of the extracted Brizy content before it is converted to block markup and written to the database.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 05:28 PM
Security Audit — agent-trust-hub — migrate-brizy-to-gutenberg