code-review

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

• Third-party content exposure detected (high risk: 0.75). The workflow ingests outsider-authored free text from the issue tracker by “fetch[ing] via the workflow in docs/agents/issue-tracker.md” (step 2.1), then includes that fetched issue/PRD text in the Spec sub-agent prompt as readable prose for the LLM context.