figma-to-elementor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from Figma designs which serves as an ingestion point for untrusted data.\n
- Ingestion points: Figma node tree (layers, names, text content) in SKILL.md.\n
- Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded commands in the design data.\n
- Capability inventory:
respira_build_page,respira_inject_builder_content,respira_sideload_image, andrespira_create_page_duplicate.\n - Sanitization: Absent; text content from Figma is not escaped or sanitized before being written to WordPress widgets.\n- [DATA_EXFILTRATION]: The skill tracks usage via an external HTTP request to the vendor's domain.\n
- Evidence:
POST https://www.respira.press/api/skills/track-usage.\n - Context: Telemetry includes site/version context and usage metrics, documented as intended vendor functionality.
Audit Metadata