internal-comms

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

• Third-party content exposure detected (medium risk: 0.30). In the skill’s runtime workflow, the agent is instructed to “gather information” from Slack and Email (and related company systems) and use those posts/emails as context, which are outsider-authored free text that can be injected into the monitored sources without the agent selecting a specific item first.