blocklet-url-analyzer

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and parses arbitrary public URLs provided as input (e.g., using curl to "${ORIGIN}/blocklet.js?type=json" and "curl -sS "$URL"" to read meta tags and APIs), thereby ingesting untrusted third‑party content that could carry indirect prompt injection.