transilience-report-style

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

• Third-party content exposure detected (medium risk: 0.30). Skill md/generator consumes user-provided report_data.json at runtime and renders its free-text fields into the PDF (including executive_summary.narrative, sections.paragraphs, and finding card fields like description, impact, recommendation, and PoC description/command), so outsider-authored text supplied into that JSON is ingested without any “fetch specific item” step.