qa-test-planner

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill contains explicit plaintext credentials (test@example.com / Test123!) and test steps that instruct entering them, which requires the LLM to 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 is explicitly triggered, and its runtime ingests free text from the caller (“Your Request” / natural-language commands like “Create a test plan for…”, including optional Figma URLs), then uses that text to generate outputs without any intermediary selection of trusted items.