playwright-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples and commands that embed secrets (cookie values, passwords, tokens) directly in CLI commands and shows capturing cookie values into shell variables, which requires the LLM to handle/output secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow (via playwright-cli goto/open + snapshot/eval/eval el.textContent) ingests page DOM text that can include outsider-authored content when the user navigates to an attacker-controlled page, so the agent is exposed to free text from that page without needing to pre-select a specific item.