gdocs-audit-report

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls get_doc() (scripts/gdocs_auth.py) and the SKILL.md workflow requires re-scanning Google Docs content (headings, runs, X-NN patterns, etc.) to build and drive batchUpdate ops, meaning it ingests user-authored Google Docs (third-party/untrusted content) that can materially influence subsequent edits/actions.