k6-playwright-converter

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

• Third-party content exposure detected (medium risk: 0.30). The skill ingests a user-supplied Playwright script at runtime (the “Given a user-supplied Playwright script…” objective) and then converts it into a generated k6/browser script, so outsider-authored free text is processed rather than constrained to trusted provider documentation.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires opening and using the embedded resources types://k6/** and docs://k6/best_practices at runtime as authoritative sources for API definitions and mapping (i.e., they directly control how the agent generates prompts/instructions and are required dependencies).