internal-comms

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses runtime “Gather information” from outsider-authored sources like Slack posts, Google Drive docs, and emails (e.g., other team members’ messages), which are free-form text not authored by the operating user and can be ingested into the LLM context.