slack-bot-builder
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs how to build bots that process untrusted data from Slack user messages and events. \n
- Ingestion points: Data enters through handlers for events like
app_mentionandmessageinapp.jsand thelisteners/directory. \n - Boundary markers: The provided code snippets do not explicitly use delimiters or specialized instructions to separate untrusted user input from the agent's internal logic. \n
- Capability inventory: The bot uses the Slack API for writing messages (
chat:write), managing views (views.open), and responding to commands. \n - Sanitization: Code examples demonstrate direct interpolation of event data (such as user IDs) into response strings without explicit validation or escaping logic.
Audit Metadata