playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt shows commands that pass and retrieve secrets (cookies, passwords, tokens) directly as command-line arguments and raw outputs (e.g., cookie-set/get, form fill with "password123", TOKEN=$(playwright-cli --raw cookie-get ...)), which requires the agent to handle and potentially emit secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can be ingested via runtime browser content: the skill navigates to arbitrary URLs (e.g., playwright-cli goto <url>), then includes page title/DOM text in the LLM-visible snapshot output and can also surface console/dialog text from that page.