playwright

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's examples and form-fill commands show embedding plaintext passwords (e.g., "$PWCLI fill e2 "password123"") which encourages including secret values verbatim in CLI commands, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly opens arbitrary public URLs and extracts/executes page content as part of its required workflows (see SKILL.md and references/workflows.md commands like pwcli open <url>, pwcli snapshot, and pwcli eval "el => el.textContent"), so untrusted third‑party webpages can be read and used to drive subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The wrapper script runs npx --package @playwright/cli playwright-cli which at runtime fetches and executes the @playwright/cli package from the npm registry (e.g. https://registry.npmjs.org/@playwright/cli), so remote code is downloaded and run as a required dependency.