playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples that embed secrets verbatim in commands (e.g., cookie-set with "abc123", filling a plaintext password, and assigning a cookie value to a TOKEN env var), which requires the LLM to handle/output secret values directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The docs describe powerful browser-automation primitives (arbitrary JS execution, eval/run-code, storage-state saving, cookie/localStorage access, tracing with full network bodies, and attach/CDP) that can be easily abused for credential theft and data exfiltration or to obtain remote control of a browser session.