setting-up-relayfile

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow is mounting/reading provider-backed files (e.g., Notion/Slack/Linear/GitHub) and exposing their contents as filesystem-readable text; those provider resources can include outsider-authored free text (e.g., page bodies, issue comments, message text) that the agent then reads into LLM context via the mounted content.md / *.json files.