aidlc-deploy

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

• Third-party content exposure detected (high risk: 0.75). Yes—during the required workflow the agent reads outsider-authored free text from the project’s existing CI/IaC and build/design markdown files (e.g., build-report.md, design/implementation.md, design/operations.md) and injects their contents into the LLM context via the “Load context”/“Reads” runtime path.