browser-automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes examples that pass plaintext passwords as command-line --fill arguments (e.g., --fill='#password=secret'), which requires the LLM to emit secret values verbatim and therefore poses an exfiltration risk.

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

• Third-party content exposure detected (low risk: 0.10). sourceName=Browser Automation with Chrome DevTools Protocol (navigate/extract/screenshot/interact); runtime path reads outsider-authored free text from the loaded web page content when a caller supplies an arbitrary URL to commands like bin/extract URL or bin/screenshot URL, causing the LLM to ingest that page text.