pentest gforge loom ai-gateway genai okta aws bedrock appsec api-security
GForge — Overview
Entry point for the GForge / AI Gateway / Loom engagement. This note is the dashboard — detail lives in the linked notes.
What These Systems Are
| Term | What It Is |
|---|---|
| GForge | Internal initiative for centralized access to LLMs — the broader programme |
| Loom | Current user-facing product under GForge; a ChatGPT-like internal chat interface based on LibreChat |
| AI Gateway | Central proxy layer that abstracts model access and is intended over time to centralize governance (model selection, budgets, rate limits) |
Note
GForge is the initiative. Loom is one current product under it. The AI Gateway is the service that actually proxies model requests. Keep the three distinct when scoping.
GForge in one sentence (from source): an internal AI gateway ecosystem where Loom currently provides the employee chat experience and the gateway proxies authenticated requests toward approved AWS-hosted model backends.
Current Request Flow
Confirmed
Both source analyses align on this path.
flowchart TD A[Internal Employee] --> B[Corporate VPN / VPC Boundary] B --> C["Genesys Loom UI<br/>(LibreChat-based)"] C --> D["Okta Authentication (PKCE)<br/>user token presented to gateway flow"] D --> E[GForge AI Gateway] E --> F["'Light LLM' component<br/>(exact name TO CONFIRM)"] F --> G[AWS Bedrock] G --> H["Approved model<br/>GLM 5 enabled in production"] H --> C
To Confirm
The exact product name, spelling, and deployment location of the “Light LLM” component must be confirmed from the repository or architecture documentation.
Supporting Secret / Configuration Path
Meeting-established path:
Internal Vault → AWS SSM Parameter Store → External Secrets Operator → application environment variablesThis is a supporting dependency of GForge/Loom. It is not automatically the primary target unless the approved scope includes the secret-injection boundary.
Detail → GForge - Architecture > Supporting Secret and Configuration Path · Related system → Vault API - Overview
Core Security Question
Important
Can an authenticated internal user make Loom or the AI Gateway perform actions, access data, invoke models/routes, or expose information beyond what that user and the approved application workflow are intended to permit?
Major Trust Boundaries (Summary)
| Boundary | Why It Matters |
|---|---|
| Corporate VPN / VPC | Network placement — internal-only, but not a substitute for app-layer controls |
| Okta / PKCE authentication | Identity establishment in the browser flow |
| Token validation at the gateway | Where identity must actually be enforced |
| Loom application authorization | Ownership of chats, projects, history |
| AI Gateway policy enforcement | Approved models, providers, routes |
| Model context boundary | Secrets and system context must not leak into prompts/responses |
| Secret injection path | Runtime secrets must not reach the browser, logs, or model context |
| Environment separation | Staging vs production parity and data isolation |
Full detail → GForge - Security Model
Current vs Planned (Summary)
| Current | Planned / Future |
|---|---|
| Loom / LibreChat web UI | Budget enforcement |
| AI Gateway model proxy | Rate-limit governance |
| AWS Bedrock routing (GLM 5) | CLI access + separate auth flow |
| Okta + PKCE authentication | Agentic email / Teams / GitHub workflows |
| Internal-only VPN/VPC placement | Additional / self-hosted models |
| Vault → SSM → secret injection | Broader model governance protocols |
| Snyk integration (in progress) | — |
Warning
Do not build active test cases for planned capabilities unless they are actually enabled and approved in the test environment.
Full matrix and scope guardrails → GForge - Current vs Planned Capabilities
Engagement Timeline
Confirmed
Targets stated in the source. Confirm at kickoff.
| Milestone | Target |
|---|---|
| Kickoff | Sep. 9 / 10 |
| Testing execution | Week of Sep. 14, approximately two weeks |
| Report | Week of Sep. 28 |
Note
Vault testing was described as taking priority over GForge. See Vault API - Pentest Game Plan.
Important Unknowns
Highest-impact open items — full list in GForge - Kickoff Questions.
- Exact Loom and AI Gateway URLs, hostnames, and API base paths
- What the “Light LLM” component actually is
- Runtime / orchestration platform (Kubernetes inferred, not confirmed)
- Authorization and role model in Loom and the gateway
- Ownership / sharing semantics for Projects and Chat History
- Whether the client can select model / provider / route directly
- Current rate limits, quotas, and budget controls
- Storage location for chat history, projects, preferences, usage records
- Transport for streaming responses (HTTP, SSE, WebSocket, other)
- Whether uploads, RAG, tools, browsing, plugins, or code execution are enabled
Relationship to GEL and Vault
Keep the systems separate during scoping.
| System | Role | Scope Note |
|---|---|---|
| GForge / Loom | AI service / application under assessment | Primary target |
| GEL | Hosting / platform context — GForge is described as deployed on GEL | GEL itself is not automatically in scope |
| Vault | Separate internal secrets service feeding AWS SSM | Already a distinct pentest target |
| AWS SSM | Secret / config backend consumed by the external secrets operator | Supporting path |
| Snyk | Automated security input; repository integration in progress | Triage input |
→ GEL - Overview · Vault API - Overview · Genesys Security Architecture - Overview
Note Map
| Note | Use During Engagement |
|---|---|
| GForge - Architecture | Components, request flow, trust-boundary detail, confidence labels |
| GForge - Security Model | Authentication, authorization, model routing, secrets, AI security principles |
| GForge - Current vs Planned Capabilities | Scope guard — what is live vs roadmap |
| GForge - Pentest Game Plan | Objectives, frameworks, phases, priorities, guardrails |
| GForge - Endpoint Inventory | Working table of Loom / gateway endpoints |
| GForge - Test Cases | Test themes and checklists by category |
| GForge - Evidence Log | Chronological observations with model/build context |
| GForge - Findings | Candidate and confirmed findings only |
| GForge - Kickoff Questions | Unknowns to resolve before and during testing |
Sources
GForge_AI_Gateway_Loom_Pentest_Gameplan_and_Security_Guidelines.docx— working security-testing reference based on the Aug. 31, 2026 meeting analysis and recap.- Architecture documentation was to be attached to the ticket from Confluence (not yet received).
Related Notes
- GForge - Architecture
- GForge - Security Model
- GForge - Current vs Planned Capabilities
- GForge - Pentest Game Plan
- GForge - Endpoint Inventory
- GForge - Test Cases
- GForge - Evidence Log
- GForge - Findings
- GForge - Kickoff Questions
- Genesys Security Architecture - Overview
- GEL - Overview
- Vault API - Overview