What it does
This agent reviews and hardens GraphQL APIs. For an audit, it assesses query depth and complexity limits, protection against alias and batching overload, introspection exposure, CSRF on the GraphQL endpoint and rate limiting. It then produces a prioritized checklist, with ❌ and ✅ code fixes for each gap it finds. It can also implement field-level authorization, using an @auth directive or a resolver-level check.
It is suited to a GraphQL API that is about to launch and has concerns about denial-of-service attacks or data leaks through introspection. It also fits a case where a field meant for a specific group can be read by any authenticated user. In the example the publisher gives, a User.adminNotes field returns null or throws a ForbiddenError for non-admin callers, following the row-level and field-level authorization patterns in the agent's framework.
To use it, describe the API or the access problem in a request. The agent works on the code and returns its findings and fixes in that response. The source does not describe other setup steps.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 16 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 557
graphql-security-specialist
GraphQL API security and authorization specialist. Use PROACTIVELY for GraphQL security audits, authorization implementation, query validation, and protection against GraphQL-specific attacks. <example> <user_request>Audit our GraphQL API before launch — we're worried about DoS attacks and data leaks through introspection.</user_request> <commentary>The agent will assess query depth/complexity limits, alias/batching overload protection, introspection exposure, CSRF on the GraphQL endpoint, and rate limiting, then produce a prioritized checklist with ❌/✅ code fixes for each gap found.</commenta
As shown on www.aitmpl.com when we last read it