playwright-skill

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow executes a JavaScript file whose contents can be provided by the user/agent; the LLM can output that file content as free-form code (outsider-authored in the sense of not being the skill’s bundled references), which is then read by run.js via fs.readFileSync(..., 'utf8') and executed.