gog-docs

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses gog --readonly --account user@example.com docs cat DOCUMENT_ID --json --wrap-untrusted, which ingests outsider-authored Google Doc body text (public/other users’ content) into the agent’s LLM context via the Docs API output wrapped as untrusted text.