playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes CLI commands that set/get cookies and fill forms with plaintext passwords (e.g., cookie-set session_id abc123, fill e2 "password123") and shows using cookie-get to capture a token into a shell variable, which requires the agent to produce or echo secret values verbatim in commands or outputs.

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can fetch arbitrary public web pages via playwright-cli goto/open/tab-new (user-supplied URLs), and the resulting page DOM/text is ingested into the agent’s LLM context through the generated snapshot/page state outputs.