Agno through 3.1.11 Code Execution via PandasTools Unsafe Reflection

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.

Remediation

1. Inventory every agno-agi agno deployment, including staging.
2. No fixed version appears in the public sources yet. Check the references below and the vendor directly.

References

• Advisoryhttps://www.vulncheck.com/advisories/agno-through-3.1.11-code-execution-via-pandastools-unsafe-reflection
• Referencehttps://github.com/agno-agi/agno
• Referencehttps://github.com/agno-agi/agno/blob/d9ab0a758286142e7d998ef313ee7504d7fd9453/libs/agno/agno/tools/pandas.py#L54
• Referencehttps://github.com/agno-agi/agno/blob/d9ab0a758286142e7d998ef313ee7504d7fd9453/libs/agno/agno/tools/pandas.py#L90
• Referencehttps://github.com/agno-agi/agno/issues/8699