migrate-thrive-architect-to-gutenberg

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain malicious instructions.
  • Ingestion points: Reads content from Thrive Architect using respira_extract_builder_content and fetches visitor comments via respira_list_review_comments (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions are used to separate the external content from the agent's logic during the mapping phase.
  • Capability inventory: The skill has significant write capabilities, including respira_update_page, respira_update_post, and respira_batch_update to modify site content.
  • Sanitization: There is no mention of escaping or sanitizing the input from Thrive Architect or review comments before processing.
  • [EXTERNAL_DOWNLOADS]: The skill sends usage telemetry to the vendor's own API.
  • Details: Sends site context and success metrics to https://www.respira.press/api/skills/track-usage (SKILL.md).
  • Context: This domain belongs to the skill's author ('respira-press') and is used for standard analytics purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 04:50 PM