slack-bot-builder
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE: No malicious patterns, obfuscation, or insecure command executions were detected. The patterns provided are consistent with official Slack developer documentation and industry best practices.- Indirect Prompt Injection (INFO): The skill provides patterns for processing external, untrusted data from Slack messages and commands. While the snippets demonstrate standard UI and API interactions, this creates an ingestion surface. 1. Ingestion points: Slack message payloads (
handle_hello), command bodies (handle_ticket_command), and incident metadata (build_notification_blocks). 2. Boundary markers: Absent in the snippets. 3. Capability inventory: Slack API calls (client.views_open,say). 4. Sanitization: Relies on Bolt framework defaults; no custom escaping is demonstrated for user-provided strings.- Data Exposure (INFO): The OAuth pattern mentions theFileInstallationStore, which stores tokens on the local filesystem. This is appropriate for development, and the documentation correctly includes a comment advising the use of database-backed stores for production environments.
Audit Metadata