gog-tasks

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime path is calling gog ... --wrap-untrusted to ingest Google Tasks content (outsider-authored user account data from Google) into the agent’s LLM context as readable text, which can include arbitrary free-form task titles/notes entered by the account’s user(s) and thus is not authored by the operating user in this chat.