dev-test-playwright

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt contains literal credential-like values (e.g., "password123", "4111111111111111") and instructs the agent to call mcp__playwright__browser_type(text="...") to enter them, which requires the LLM to emit secret values verbatim in commands/outputs.

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via Playwright MCP’s runtime page accessibility tree/snapshots (mcp__playwright__browser_snapshot()), which will include arbitrary text rendered by whatever external site the agent navigates to (public web content or other users’ content).