qa-test-planner

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and extract design specifications from external Figma URLs (see SKILL.md, README.md, and references/figma_validation.md) — untrusted third‑party content the agent is expected to read and use to generate validation test cases and bug reports, which can materially influence subsequent actions.