php-networking

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

• Third-party content exposure detected (high risk: 0.90). The skill includes runnable examples that fetch and ingest arbitrary external URLs (e.g., the Multi-cURL section that does curl_init($url) for items in $urls and collects responses via curl_multi_getcontent), which clearly exposes the agent to open/public third‑party content that could contain untrusted, user-generated input.