analyzing-malicious-url-with-urlscan

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly instructs including an API key in the request header ("Header: API-Key: your-api-key"), which encourages embedding a secret verbatim into generated API calls and thus requires the LLM to handle/output secret values directly.

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

• Third-party content exposure detected (high risk: 0.75). The required workflow submits a user-supplied suspicious URL to URLScan and then ingests URLScan API response fields (including rendered DOM content and other page-derived text) into the agent’s processing context, which is outsider-authored free text originating from the scanned third-party web page.