maestro-amend

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

• Third-party content exposure detected (high risk: 0.72). Outsider free text can enter the LLM context via runtime ingestion of user-supplied directories/files for --from-verify/--from-review/--from-issues and via --scan reading .workflow/ artifacts (e.g., issues.jsonl, review.json, execution summaries) that may contain third-party-authored text; the skill then parses/extracts those contents into signals for diagnosis and overlay drafting.