eve-read-eve-docs

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly ingests and acts on user-generated third-party content—e.g., inbound Slack messages, chat thread messages, and cloud FS/Google Drive-mounted files (see references/agents-teams.md and references/integrations.md) which are injected into coordination inboxes and agent job context and can drive agent commands and job actions.