superdesign

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

• Third-party content exposure detected (low risk: 0.10). The required workflow involves reading live websites via the extract-website tool and direct public image/webpage URLs provided by users at runtime, which constitutes low-risk ingestion of outsider-authored web content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill references https://raw.githubusercontent.com/superdesigndev/superdesign-skill/main/skills/superdesign/references/INIT.md in INIT.md and https://raw.githubusercontent.com/superdesigndev/superdesign-skill/main/skills/superdesign/references/SUPERDESIGN.md in SUPERDESIGN.md as remote fallback fetch locations.