build-oxygen6-page
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from existing WordPress sites (e.g., through element schemas and existing page node trees) and use that data to generate new layouts.
- Ingestion points: Data is retrieved via
respira_get_builder_infoand by reading existing page trees or source content during rebuilds. - Boundary markers: The skill does not define specific boundary markers or instructions to ignore embedded prompts within the site content being read.
- Capability inventory: The skill utilizes
build_pageandinject_builder_contenttools to write content back to the WordPress database. - Sanitization: No explicit sanitization or validation steps are defined for the incoming site data before it is processed by the agent.
- [DATA_EXFILTRATION]: The skill includes a telemetry endpoint (
https://www.respira.press/api/skills/track-usage) to track skill usage. This endpoint belongs to the official domain of the skill author and is used for metadata reporting.
Audit Metadata