penpot-audit-accessibility

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow uses execute_code to run penpotUtils.analyzeDescendants and scripts/collectAccessibilityData.js, which ingests the design’s shape tree (outsider-authored design content from the audited page/selection) as readable text fields like s.name/s.characters into the LLM context for report generation.