AI AgentHigh severity · automated estimate
CVE-2026-119050: Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers…
- Occurred
- Oct 29, 2026
- Published
- Oct 29, 2026
- Source
- NVD CVE
Summary
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.
Likely agent failure (automated tag)
- Direct prompt injection
- Tool selection failure
Likely cause (automated tag)
- Missing or unenforced guardrail
Tags
- CVE
- CVE-2026-119050
- cvss:HIGH
Automated classification
Category confidence: 95%
Severity confidence: 90%
Classifier note (automated): Agent vulnerability allows arbitrary code execution via prompt injection and unsafe reflection in tool usage.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8