internal-comms

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow explicitly instructs gathering information from Slack/email/Drive/Calendar, which can include outsider-authored free-form text (e.g., other employees’ Slack posts or emails) that may be ingested into the agent’s LLM context for drafting comms.