playwright-pro

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

• Third-party content exposure detected (low risk: 0.10). The skill reads user-provided $ARGUMENTS (e.g., /pw:generate <spec> allows a “URL” or component name) to drive code generation, but it does not specify any runtime fetching/ingestion of arbitrary outsider-authored free text into the LLM beyond reading the user’s project files/templates.