Affected Technology
BerriAI/litellm incidents
LiteLLM proxy for calling 100+ LLM APIs
PyTorch Remote Code Execution Vulnerability
A vulnerability in the HuggingFace Transformers library, specifically in the `Trainer` class, allows for arbitrary code execution. The `_load_rng_state()` method in `src/transformers/trainer.py` at line 3059 calls `torch.load()` without the `weights_only=True` parameter. This issue affects all versions of the library supporting `torch>=2.2` when used with PyTorch versions below 2.6, as the `safe_globals()` context manager provides no protection in these versions. An attacker can exploit this vulnerability by supplying a malicious checkpoint file, such as `rng_state.pth`, which can execute arbitrary code when loaded. The issue is resolved in version v5.0.0rc3.
LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request
### Impact Any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination they control and cause the proxy to send its own configured provider credentials to that destination. The proxy's request-body validation was a denylist that did not cover every sensitive parameter and did not inspect parameters nested inside other request fields, so a caller could supply a routing or credential value that the proxy applied without clearing the operator's stored key. Any authenticated user could therefore exfiltrate the operator's upstream provider credentials and other configured secrets, and perform Server-Side Request Forgery against internal services reachable from the proxy. ### Patches Fixed in 1.96.2, 1.95.1, 1.94.3, 1.93.2, 1.92.2, 1.91.5, 1.90.7, 1.89.7, and 1.88.6. ### Workarounds Set `general_settings.allow_client_side_credentials` to `false` so callers cannot override connection parameters, restrict proxy keys to trusted callers, and block the affected parameters (`api_base`, `base_url`, `model_list`, `fallbacks`, provider credential fields) at a reverse proxy or API gateway.
LiteLLM Security Incident
### Summary A server-side request forgery in LiteLLM Proxy lets an authenticated caller redirect the proxy's outbound request to a host of their choosing by smuggling an `api_base` inside the `user_config` request body, bypassing the existing parameter guard. ### Details LiteLLM Proxy validates request bodies with `is_request_body_safe`, which blocks the `api_base` and `base_url` parameters but does not cover `user_config`. The `user_config` object is used to build the outbound router for a request, so a caller can place an `api_base` inside it and reach an arbitrary host. The guard only inspected the two top-level keys, so the same `api_base` nested inside `user_config` was never checked. Exploitation requires a valid virtual key. ### Impact An authenticated caller can make the proxy issue server-side requests to internal or external hosts of their choosing, reaching endpoints the caller cannot otherwise access. ### Affected / Patched Affected: `