browser-testing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes example CLI commands that embed literal credentials (e.g., playwright-cli fill ... "password123"), which requires the agent to output secret values verbatim in generated commands or scripts.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow drives playwright-cli/Browser-Use to load pages on URLs and then ingests attacker-controlled page text via accessibility snapshots and console/network outputs (e.g., login/contact pages), which can be poisoned by outsiders through those web application surfaces.