slack-daily-digest
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- Processing of External Data: The skill retrieves content from Slack messages and threads. This involves processing untrusted data from Slack which could contain indirect prompt injections. The ingestion points include
slack_read_channel,slack_read_thread, andslack_search_public_and_privateinSKILL.md. No specific boundary markers or sanitization logic are present for this external content. - Capability Inventory: The skill has the capability to write messages back to Slack by calling
../slack-outgoing-message/SKILL.md. This write capability is gated by explicit user intent. - Tool Integration: The workflow relies on standard Slack tools for searching and reading data. It does not perform any unauthorized data exfiltration or external network requests beyond the Slack environment.
Audit Metadata