playwright-python

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes plaintext passwords in code and test examples (e.g., "hunter2" / "hunter2-pls"), which demonstrates embedding secret values directly into generated code/commands and therefore requires the LLM to handle/output secrets verbatim.

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

• Third-party content exposure detected (high risk: 0.90). Yes—this skill’s runtime flow uses Playwright to navigate to a user-supplied URL and then serializes the page’s outsider-authored rendered content (e.g., HTML/text from page.content(), page.inner_text(), or page.accessibility.snapshot() in scripts/dom.py and scripts/snapshot.py) which is then available to the agent via the tool/read of the produced output file.