playwright

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes an example that embeds plaintext credentials in CLI commands (e.g., "$PWCLI" fill e2 "password123"), which requires the LLM to output secret values verbatim and thus is insecure.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The wrapper script invokes npx at runtime to fetch and execute the npm package @playwright/cli (npx --package @playwright/cli playwright-cli), which downloads and runs remote code from the npm registry (e.g. https://registry.npmjs.org/@playwright/cli).