Vulnerability · Published Mar 31, 2026 · Assigned by GitHub_M
CVE-2026-34172Giskard Agents have Server-side template injection via ChatWorkflow.chat() using non-sandboxed Jinja2 Environment
High 7.7
In plain English
A high-severity security flaw in giskard-oss from Giskard-AI. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 51% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
Giskard is an open-source Python library for testing and evaluating agentic systems. Prior to versions 0.3.4 and 1.0.2b1, 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. This issue has been patched in versions 0.3.4 and 1.0.2b1.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | giskard-agents | 0.3.4 | GHSA-frv4-x25r-588m |
| PyPI | giskard-agents | 1.0.2b1 | GHSA-frv4-x25r-588m |
| PyPI | giskard-agents | 0.3.4, 1.0.2b1 | PYSEC-2026-2487 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| Giskard-AI | giskard-oss | < 0.3.4>= 1.0.1a1, < 1.0.2b1 |
Weakness: CWE-1336 · Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N