GHSA-3wp3-xxj9-5jqq

## Summary

The `get_all_models` handlers in `routers/openai.py` and `routers/ollama.py` intended to cache their **permission-filtered** model lists per user, but the `@cached` decorator was misconfigured: it passed a `key=` lambda instead of `key_builder=`. In aiocache 0.12.3 (the pinned version), `key=` is a **static** cache key — a callable passed there is used as a constant object, not invoked per call. As a result the per-user key was never computed, and all callers collided onto a single shared cache entry within the TTL window. During that window, one user's permission-filtered model list could be served to a different authenticated user, crossing the per-user authorization boundary.

## Impact

- **Boundary crossed:** Confidentiality (cross-user). A caller can receive the model list scoped to a *different* security principal than themselves. - A user (or admin, or — depending on endpoint reachability — anonymous caller) who populates the cache causes the next caller within the TTL to receive *that* list rather than their own permission-filtered one. - What's disclosed is the set of models another principal can access, including potentially the existence and naming of models restricted from the receiving user. - Exposure is **incidental and timing-dependent**, not attacker-controlled: the leaked entry is whatever the most recent caller populated within `MODELS_CACHE_TTL` (default 1 second), and the attacker cannot select the victim or force a target's list into the cache.

## Affected component

- `backend/open_webui/routers/openai.py` — `get_all_models` (~line 488) - `backend/open_webui/routers/ollama.py` — `get_all_models` (~line 302)

Both decorated with `@cached(ttl=MODELS_CACHE_TTL, key=lambda ...)`. No other `@cached(... key=lambda ...)` misuse was found elsewhere in the backend.

## Root cause

aiocache 0.12's `@cached` treats `key=` as a static key; the per-call hook is `key_builder=` with signature `key_builder(func, *args, **kwargs)`. Passing a callable to `key=` uses the callable object itself as a constant key, so every invocation resolved to the same entry and the intended per-`user.id` namespacing never occurred.

## Reproduction (default config)

1. On a default deployment, configure at least two users with *different* model-access permissions (e.g. one model restricted to user A). 2. As user A, request the model list (populates the shared cache entry). 3. Within `MODELS_CACHE_TTL` (default 1s), as user B, request the model list. 4. User B receives user A's permission-filtered list, including models B is not permitted to see.

## Remediation

Replace `key=` with `key_builder=` at both call sites and adjust the lambda to take the function as its first argument:

```python @cached( ttl=MODELS_CACHE_TTL, key_builder=lambda _func, request, user=None: ( f'openai_all_models_{user.id}' if user else 'openai_all_models' ), ) ```