a365-code-validator

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads and parses free text from the user’s local target project files (e.g., it recursively reads *.py, *.ts/.js, .env*, and config JSON and the standalone validator concatenates contents and regex-matches them), which is outsider-authored when the repo is authored by an untrusted user.