slack-bot-builder
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for Slack bots that process untrusted data from Slack users, creating a standard surface for indirect prompt injection.
- Ingestion points: The
messageobject inhandle_helloand thebodyobject inhandle_ticket_commandinSKILL.mdingest untrusted input from the Slack platform. - Boundary markers: The provided patterns do not include explicit instructions or markers to delimit untrusted user content from agent instructions.
- Capability inventory: The bot code demonstrates capabilities for sending messages via
say()and opening interactive modals viaclient.views_open()inSKILL.md. - Sanitization: The code snippets do not show validation or sanitization of input data before processing.
Audit Metadata