unblocked-context-search-messages

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly calls context_search_messages to retrieve messages from Slack and Microsoft Teams (see SKILL.md "Sources: Slack, Microsoft Teams" and the context_search_messages invocation), so the agent ingests untrusted, user-generated chat content that can influence follow-up queries and actions.