recipe-plugin-compliance

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

• Third-party content exposure detected (high risk: 0.75). The workflow reads marketplace bundle/module/package content (Step 3: architecture module --module {module_name} --full and then iterates packages/affected_files), which is outsider-authored free text from public marketplace bundles and is then used to generate deliverables and solution-outline content in the LLM context.