qa-flow-report

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires capturing “all” console messages and the “full network log” and recording them in the manifest/report, which can include Authorization headers, cookies, query params, or other secrets, so the agent would need to include secret values verbatim in its output.

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and workflow explicitly drive arbitrary target URLs via the mcp__chrome-devtools__navigate_page and related tools and then read/interpret page DOM, console messages, and network requests (see "Step loop" in SKILL.md and the use of list_console_messages/list_network_requests), which clearly ingests untrusted third‑party web content that can influence subsequent actions.