uat-nonit-testcase

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt instructs using Playwright to set localStorage accessToken and add cookies for an auth "dev-token" bypass, which implies embedding real tokens/credentials into generated scripts or commands (verbatim) and thus risks secret exfiltration.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md:72-74 requires “Lấy lời business user nguyên văn” (outsider-authored free-form text from a business user) and then uses it to generate the HTML deliverable, which implies that this free text is ingested into the agent’s LLM context during runtime.