webapp-testing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples that embed plaintext credentials (e.g., "Enter password 'testpass'") directly in task instructions sent by the agent, which requires the LLM to output secret values verbatim and therefore poses a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates to and ingests arbitrary public URLs (see SKILL.md browser_subagent Task examples requiring "Navigate to " and scripts/playwright_runner.py which calls page.goto(url) and returns page title, console errors, and other extracted page data), so untrusted third‑party page content can be read and materially influence the agent's actions.