browser-testing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly shows and encourages embedding passwords/credentials directly into CLI commands (e.g., --value "SecurePass123"), which requires the LLM to handle and output secret values verbatim and thus creates exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow includes navigating to a user-supplied URL (navigation go-to --url ...) and then capturing page content (content get-as-html/get-as-text), which can ingest outsider-authored free text from arbitrary public web pages into the agent’s LLM context.