- CVSS
- HIGH · 8.1v3.1CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
- Published
- 2026-10-29
- Weakness
- CWE-470
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-119050
Description
Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to getattr(). Attackers can use prompt injection to make the agent call pandas.read_pickle on attacker-controlled paths for code execution, or call other readers to read local files.
References
- https://github.com/agno-agi/agno
- https://github.com/agno-agi/agno/blob/d9ab0a758286142e7d998ef313ee7504d7fd9453/libs/agno/agno/tools/pandas.py#L54
- https://github.com/agno-agi/agno/blob/d9ab0a758286142e7d998ef313ee7504d7fd9453/libs/agno/agno/tools/pandas.py#L90
- https://github.com/agno-agi/agno/issues/8699
- https://www.vulncheck.com/advisories/agno-through-3.1.11-code-execution-via-pandastools-unsafe-reflection
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-119050 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.