asc-localize-metadata

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

• Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text can enter the LLM context via Step 3 “Translate with LLM,” where the agent reads downloaded App Store metadata files (e.g., ./localizations/en-US.strings and ./app-info-localizations/en-US.strings) that originate from App Store Connect content authored by others (not the operating user), and then injects those strings into the LLM prompt template.