Chrome Bridge Automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains explicit examples that embed credentials directly into CLI/act prompts (e.g., filling a password 'pass123' in an act command), which requires the LLM to handle/output secret values verbatim and thus poses an exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly connects to the user's real Chrome browser and navigates arbitrary web pages (see the "Connect to a Web Page" command npx @midscene/web@1 --bridge connect --url ... plus the required take_screenshot and act steps) and requires the agent to read screenshots of those pages to decide actions, exposing it to untrusted public web content that can influence behavior.