design-compliance

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt contains hardcoded login credentials (Username: apvhn / Password: apvhn) and instructs the agent to perform automated authentication in a headless browser, which would require embedding those secret values verbatim into generated scripts or requests.

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

• Third-party content exposure detected (high risk: 0.90). The skill's URL Mode and Step 4 Visual Inspection explicitly instruct the agent to open and analyze user-provided or public webpages in a headless browser (Playwright) — and to fetch external docs — so untrusted third-party page content would be read and could directly influence automated analysis and in-place code edits.