konnect-app-auth
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates the diagnostic process for Konnect Dev Portal authentication. It uses established tools like
terraform-konnect,kongctl-declarative, and thekong-konnectMCP server to interact with the environment, which is standard behavior for managing Konnect resources. - [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection due to its interaction with live environment data and repository artifacts.
- Ingestion points: The
kong-konnectMCP server (inspecting portals, registrations, and approvals) and user-provided repository context (HCL and declarative configuration files). - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the ingested data.
- Capability inventory: The skill uses
terraform,kongctl, anddeckto modify infrastructure and gateway state. - Sanitization: There is no evidence of explicit sanitization or validation logic applied to data retrieved from external tools before it is processed by the agent.
Audit Metadata