Agenta-AI vulnerabilities and threats

Agenta is an open-source LLMOps platform. A Server-Side Template Injection (SSTI) vulnerability exists in versions prior to 0.86.8 in Agenta's API server evaluator template rendering. Although the vulnerable code lives in the SDK package, it is executed server-side within the API process when running evaluators. This does not affect standalone SDK usage — it only impacts self-hosted or managed Agenta platform deployments. Version 0.86.8 contains a fix for the issue.

Agenta is an open-source LLMOps platform. In Agenta-API prior to version 0.48.1, a Python sandbox escape vulnerability existed in Agenta's custom code evaluator. Agenta used RestrictedPython as a sandboxing mechanism for user-supplied evaluator code, but incorrectly whitelisted the `numpy` package as safe within the sandbox. This allowed authenticated users to bypass the sandbox and achieve arbitrary code execution on the API server. The escape path was through `numpy.ma.core.inspect`, which exposes Python's introspection utilities — including `sys.modules` — thereby providing access to unfiltered system-level functionality like `os.system`. This vulnerability affects the Agenta self-hosted platform (API server), not the SDK when used as a standalone Python library. The custom code evaluator runs server-side within the API process. The issue is fixed in v0.48.1 by removing `numpy` from the sandbox allowlist. In later versions (v0.60+), the RestrictedPython sandbox was removed entirely and replaced with a different execution model.