inngest-setup

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npm and npx to download and run the inngest SDK and inngest-cli from the official npm registry. These are well-known tools associated with the Inngest service.
  • [COMMAND_EXECUTION]: The instructions include shell commands for installing dependencies and running the local development server using tsx and npx. The command npx --ignore-scripts=false inngest-cli@latest dev explicitly enables package scripts, which is a common requirement for this tool's development server.
  • [PROMPT_INJECTION]: The skill sets up an environment for processing external data (events and webhooks), which constitutes an indirect prompt injection attack surface.
  • Ingestion points: External event payloads and webhook data processed by inngest.createFunction in SKILL.md.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are provided in the setup templates to delimit untrusted event data.
  • Capability inventory: Configured functions run within the application's TypeScript environment and have access to any tools or network capabilities granted to the service.
  • Sanitization: The skill provides basic setup code without explicit input validation or sanitization logic for the ingested event payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 07:20 PM
Security Audit — agent-trust-hub — inngest-setup