backend-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from multiple untrusted sources, creating an attack surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through
formDatain Server Actions withinapp/actions/users.ts, raw request bodies in Supabase Edge Functions insupabase/functions/process-webhook/index.ts, and event data payloads in Inngest background functions ininngest/functions.ts. - Boundary markers: The instructions advise using Zod validation and session-based authentication checks as logical boundaries to isolate external content processing.
- Capability inventory: The skill includes instructions for database mutations using Prisma and Supabase clients, as well as network operations via
fetchand event dispatching tools. - Sanitization: The skill explicitly requires the use of Zod schemas to validate and sanitize all external inputs prior to any execution or storage logic.
- [COMMAND_EXECUTION]: The skill instructs the agent to run discovery commands to audit the existing environment.
- In the
Check existing firstsection ofSKILL.md, the agent is directed to usels,cat, andrgto inspect project structure and configuration files likepackage.jsonandprisma/schema.prisma. These are benign discovery operations intended for architectural analysis. - [EXTERNAL_DOWNLOADS]: The skill references and integrates libraries from well-known service providers and public CDNs.
- It imports the Supabase JavaScript SDK from the
esm.shcontent delivery network for Edge Function implementation. - It utilizes established Node.js packages such as
@upstash/ratelimit,@upstash/redis, andinngestfor essential backend functionality.
Audit Metadata