Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍 PyPI

GHSA-frv4-x25r-588m

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

Also known asCVE-2026-34172
Published
Mar 27, 2026
Updated
Mar 31, 2026
Affected
2 pkgs
Patched
2 / 2
Exploits
None indexed

EPSS Exploitation Probability

via FIRST.org ↗
0.6%probability of exploitation in next 30 days
Lower Risk45th percentile+0.27%
0.00%0.37%0.74%1.11%0.4%0.3%0.3%0.6%Apr 26Jun 26Jun 26

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

Blast Radius

2 pkgs affected
🐍giskard-agents🐍giskard-agents

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

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:

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:

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:

_inline_env = Environment(
    autoescape=False,
    # Not SandboxedEnvironment
)

Proof of Concept

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:

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.

Affected Packages

2 total 2 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIgiskard-agentsall versions0.3.4
🐍PyPIgiskard-agents1.0.1a1&&< 1.0.2b11.0.2b1

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for giskard-agents. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update giskard-agents to 0.3.4 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-frv4-x25r-588m is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether GHSA-frv4-x25r-588m is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to GHSA-frv4-x25r-588m. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

## 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")
O3 Security · Impact-Aware SCA

Is GHSA-frv4-x25r-588m in your dependencies?

O3 detects GHSA-frv4-x25r-588m across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.

GHSA-frv4-x25r-588m: giskard-agents Remote Code Execution | O3 Security