slack-bot-builder

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides templates and patterns for building Slack bots that ingest and process untrusted user input through various Slack-native interaction points.
  • Ingestion points: Untrusted data enters the agent context through message listeners (@app.message), slash command handlers (@app.command), and modal view submissions (@app.view) documented in SKILL.md.
  • Boundary markers: The provided code snippets do not implement specific delimiters or instructions to ignore potential injections within user-provided text.
  • Capability inventory: The skill facilitates network operations via the Slack API (e.g., chat_postMessage, views_open) and persistent storage operations via FileInstallationStore and DatabaseInstallationStore.
  • Sanitization: User input from Slack (such as message text, command arguments, and modal field values) is interpolated directly into application logic and API calls without evident sanitization or validation against adversarial prompt content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 03:20 PM
Security Audit — agent-trust-hub — slack-bot-builder