migrate-divi-to-bricks

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs telemetry via a POST request to https://www.respira.press/api/skills/track-usage. This domain is the official site of the developer ('respira-press'). The data collected involves usage metrics (duration, success status, and element counts) and site context, which is a standard practice for maintaining vendor-provided skills.
  • [PROMPT_INJECTION]: As the skill processes user-controlled WordPress content, it possesses an indirect prompt injection attack surface. This risk is mitigated by the skill's design:
  • Ingestion points: Data is ingested from the WordPress post_content field via the wordpress_extract_builder_content tool as defined in SKILL.md.
  • Boundary markers: The agent is instructed to generate a migration plan and wait for explicit user approval before proceeding to the injection phase.
  • Capability inventory: The skill uses managed WordPress tools for all database operations; it contains no shell execution, code evaluation, or unauthorized file access.
  • Sanitization: The migration process includes decoding of common content encodings (HTML entities and percent-encoding) and requires the creation of draft duplicates rather than modifying original records.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 05:29 PM
Security Audit — agent-trust-hub — migrate-divi-to-bricks