slack-bot-builder
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of Slack bots that ingest untrusted data from external sources (user messages and slash commands), which is a common surface for indirect prompt injection attacks.
- Ingestion points: Untrusted data enters the application context through
app.message()handlers and thebodyparameter ofapp.command()handlers inSKILL.md. - Boundary markers: The provided code snippets do not include specific delimiters or instructions to the agent to ignore embedded commands within user input.
- Capability inventory: The skill patterns allow for Slack API interactions, including sending messages via
say()and managing UI components viaclient.views_open()as shown inSKILL.md. - Sanitization: The examples do not demonstrate explicit sanitization or filtering of the incoming message strings or command payloads.
Audit Metadata