axiom-asc-mcp

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and processes user-generated App Store reviews via the "Review Management" workflow (e.g., reviews_list → reviews_create_response), which are untrusted third‑party contents from App Store Connect that the agent is expected to read and act on when crafting responses — enabling potential indirect prompt injection.