asset-prep

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

• Third-party content exposure detected (low risk: 0.10). The agent skill required workflow includes running scripts (like brand.mjs and capture.mjs) that fetch and extract content from arbitrary external websites supplied as URLs, which exposes the LLM to outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script fetches a font inventory via CDN URL at runtime (https://cdn.jsdelivr.net/npm/simple-icons@latest/...), fulfilling an official or reputable third-party operational dependency which is common/reputable.