Giskard Agents have Server-side template injection via ChatWorkflow.chat() using non-sandboxed Jinja2 Environment
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 0.3.4, 1.0.2b1
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
- Exploitation: poc
- Automatable: no
- Technical impact: total
Summary
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.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: poc · Automatable: no · Technical impact: total
- Record last updated
Affected versions
- Giskard-AI giskard-oss
fixed in 0.3.4; From 1.0.1a1 · fixed in 1.0.2b1
- giskard-agentsPyPI
fixed in 0.3.4
- giskard-agentsPyPI
From 1.0.1a1 · fixed in 1.0.2b1
- giskard-agentsPyPI
fixed in 0.3.4; From 1.0.1a1 · fixed in 1.0.2b1