pentest gforge loom ai-gateway genai okta aws bedrock ssm appsec
GForge — Architecture
System understanding for GForge / Loom / AI Gateway. Information is classified by confidence — never treat an inference as architecture fact.
Security controls and boundaries → GForge - Security Model. Scope of what is live → GForge - Current vs Planned Capabilities.
Confidence Legend
| Label | Meaning |
|---|---|
| CONFIRMED | Explicitly stated or demonstrated in the source |
| PLANNED | Discussed as future capability — not assumed live |
| INFERRED | Reasonable interpretation requiring validation |
| TO CONFIRM | Insufficient evidence |
Components
| Component | Role | Confidence |
|---|---|---|
| Genesys Loom | Employee-facing chat UI, LibreChat-based | Confirmed |
| GForge AI Gateway | Central proxy abstracting model access | Confirmed |
| “Light LLM” | Component between the gateway and Bedrock | Confirmed it exists; exact name/product/deployment To Confirm |
| AWS Bedrock | Model hosting / routing backend | Confirmed |
| GLM 5 | Model stated as the only production-enabled model at meeting time | Confirmed |
| Okta (PKCE) | Browser authentication flow | Confirmed |
| Corporate VPN / VPC | Internal-only network placement | Confirmed |
| GEL | Platform GForge is described as deployed on | Confirmed |
| Internal Vault → AWS SSM → External Secrets Operator | Runtime secret/config injection path | Confirmed |
| Runtime / orchestration platform | Container orchestration | To Confirm — Kubernetes was inferred from “external secrets operator”, not confirmed |
| Chat history / projects / preferences storage | Data stores | To Confirm |
Current Request Flow
Confirmed
Both source analyses align on this path.
flowchart TD U[Internal Employee] --> VPN[Corporate VPN / VPC Boundary] VPN --> LOOM["Genesys Loom UI<br/>LibreChat-based"] LOOM --> OKTA["Okta Authentication (PKCE)"] OKTA --> GW[GForge AI Gateway] GW --> LLLM["'Light LLM' component<br/>name TO CONFIRM"] LLLM --> BR[AWS Bedrock] BR --> M["Approved model<br/>GLM 5 (production-enabled)"] M --> LOOM
Step detail:
- Internal employee reaches the service from inside the corporate network.
- Traffic crosses the corporate VPN / VPC boundary — the service is internal-only.
- Genesys Loom UI (LibreChat-based) serves the chat experience.
- Okta authentication using PKCE; the user token is presented to the gateway flow.
- The GForge AI Gateway receives the request.
- The “Light LLM” component sits between the gateway and Bedrock.
- AWS Bedrock routes to the approved model.
- GLM 5 was the production-enabled model at meeting time.
- The model response returns through the same path to Loom.
To Confirm
- Exactly where PKCE is terminated and where token validation is enforced.
- Whether Loom and the AI Gateway have separately reachable endpoints.
- The transport used for chat responses (normal HTTP, streaming SSE, WebSocket, other).
Supporting Secret and Configuration Path
Confirmed
Meeting-established path.
flowchart LR V[Internal Vault] --> SSM[AWS SSM Parameter Store] SSM --> ESO[External Secrets Operator] ESO --> ENV[Application Environment Variables]
This is a supporting dependency, not automatically the primary target. It enters scope only if the approved scope includes the secret-injection boundary.
To Confirm
Whether the “Internal Vault” in this path is the same service as the Vault API assessed separately in Vault API - Overview, or a different internal Vault component. The GForge source does not establish this.
Warning
Avoid turning GForge testing into a standalone Vault pentest. Trace only the approved application-facing portions. Vault has its own engagement — see Vault API - Pentest Game Plan.
Network and Hosting Placement
| Aspect | Detail | Confidence |
|---|---|---|
| Exposure | Internal-only, behind corporate VPC / VPN | Confirmed |
| Hosting | Deployed on GEL | Confirmed |
| Orchestration | Container platform unspecified — Kubernetes inferred only | To Confirm |
| Environments | Staging environment exists, intended to mirror production as closely as possible for the pentest | Confirmed |
Important
Internal-only placement is one boundary, not the whole security model. Application controls must still enforce identity and permissions. See GForge - Security Model > Trust Boundaries.
Model Routing
| Item | State | Confidence |
|---|---|---|
| AWS Bedrock as routing backend | Current | Confirmed |
| GLM 5 production-enabled | Current | Confirmed (at meeting time) |
| Kimi 2.5, Qwen 2.5 | Planned / future | Confirmed as future |
| Self-hosted / open-source model routes | Planned / future | Confirmed as future |
| Direct Hugging Face enablement | Not planned | Confirmed — the meeting explicitly stated models would be governed/hosted through AWS rather than direct Hugging Face enablement |
| Bedrock guardrails / model-governance controls active | Unknown | To Confirm |
Full capability matrix → GForge - Current vs Planned Capabilities
Source Reconciliation
How the two source analyses compared, per the document.
| Topic | Assessment | Working Interpretation |
|---|---|---|
| GForge purpose | Both sources align | Centralized internal AI gateway; Loom is a chat product/interface under the initiative |
| Current request path | Both sources align | Loom → AI Gateway → Light LLM → AWS Bedrock; Okta/PKCE part of the current auth flow |
| Network placement | Both sources align | Internal-only, behind corporate VPC/VPN; deployed on GEL |
| Secrets | Both sources align | Internal Vault → AWS SSM → external secrets operator → application environment |
| Snyk | Reconciled | Transcript says integration is in progress — treat as an active workstream, not necessarily fully deployed |
| Timeline | Complementary | Kickoff Sep. 9/10; testing from week of Sep. 14 for ~2 weeks; report week of Sep. 28 |
| Kubernetes | Not confirmed | One analysis inferred Kubernetes from “external secrets operator”. Keep orchestration technology as To Confirm |
Architecture Questions
Open architecture items are tracked in GForge - Kickoff Questions > Architecture. Highest priority:
- Obtain the Confluence architecture diagram referenced in the meeting
- Identify what “Light LLM” is and where it is deployed
- Confirm runtime / orchestration technology
- Locate storage for chat history, projects, preferences, and usage/accounting records
Sources
GForge_AI_Gateway_Loom_Pentest_Gameplan_and_Security_Guidelines.docx(Aug. 31, 2026 meeting analysis and recap).- Confluence architecture documentation — to be attached to the ticket, not yet available.