Skip to content

← Public intelligence

PyPI package

giskard-agents

Open actionable advisories and recorded vendor fixes. This public package view has no inventory attached and cannot establish whether your deployment is affected. A vendor fix never resolves your finding; verify your installed version and the source guidance.

Open advisories

1 actionable advisory, newest first. Withdrawn advisories and news are excluded. Coverage is partial.

  1. High, CVSS 7.7PyPIAmendedPublished

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

    CVE-2026-34172 · GHSA-frv4-x25r-588m

    Affected
    • PyPI giskard-agents <= 0.3.3; >= 1.0.1a1, <= 1.0.2a1
    Fixed in
    0.3.41.0.2b1· Vendor fix available
    Issue
    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: The string becomes contenttemplate, which is parsed by fromstring(): libs/giskard-agents/src/giskard/agents/templates/message.py lines 14-15: The Jinja2 Environment is not sandboxed: libs/giskard-agents/src/giskard/agents/templates/environment.py line 37: Proof of Concept A developer building a chatbot: Note: using .withinputs(var=userdata) 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…

    Recommended action: Upgrade to 1.0.2b1 (pre-release) or 0.3.4 by release line, then redeploy and verify.A vendor fix does not resolve your finding until you verify it in your own systems.

    Sources:osv.dev (1)github.com (2)Source checked Evidence →