openai-playwright

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's recommended CLI/form-fill examples include plaintext credentials (e.g., fill e2 "password123") and instruct emitting commands that embed secret values verbatim, which would require the LLM to output secrets directly.

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

• Third-party content exposure detected (high risk: 1.00). This skill automates a real browser and explicitly instructs the agent to open and scrape arbitrary public web pages (e.g., commands like pwcli open https://example.com, pwcli snapshot, and pwcli eval "el => el.textContent" e12 in SKILL.md and references/cli.md), so it will fetch and interpret untrusted, user-generated third-party web content.