migrate-oxygen-to-breakdance

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill sends usage telemetry including success status, pages audited, and site context to "https://www.respira.press/api/skills/track-usage". This domain belongs to the identified author ("respira-press").
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted builder data from the Oxygen Builder database, which could contain embedded malicious instructions targeting the AI agent during the mapping process.
  • Ingestion points: Reads Oxygen builder shortcodes from post_meta via "respira_extract_builder_content" in "SKILL.md".
  • Boundary markers: No explicit delimiters or instructions to ignore embedded content are defined when processing the extracted builder JSON.
  • Capability inventory: The skill has permissions to write to the WordPress database ("respira_inject_builder_content", "respira_update_element"), create new pages ("respira_create_page_duplicate"), and perform network operations.
  • Sanitization: There is no evidence of sanitization or structural validation performed on the extracted content before it is processed for mapping.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 03:53 AM