LLAMA-INDEX-PACKS-FINCHAT · CVE-2024-12909 · Package
FIX → 0.3.0
The FinanceChatLlamaPack in the llama-index-packs-finchat PyPI package builds SQL in its database_agent run_sql_query function without sanitizing input, so an attacker can inject arbitrary SQL. Per the advisory, this can be chained through PostgreSQL large object functions to achieve remote code execution.
first public Mar 20, 2025 · 1 public exploit · 2 sources
Check it with your coding agent
It reads this page and tells you if your code or app is affected.
Teams that installed the llama-index-packs-finchat package, which is affected up to and including version 0.3.0, and that expose its database_agent to untrusted input. The maintainers resolved it by no longer supporting the package and moving it to a stale_packages branch, so no patched release is stated. Teams that do not use this pack can skip it.
Not affected if no-database-agent, not-using-finchat-pack, package-not-installed
Who cares ai-agents, llama-index, postgresql, python
llama-index-packs-finchat is installed: pip show llama-index-packs-finchat0.3.0 or lower to be affectedUpgrade to 0.3.0
A vulnerability in the FinanceChatLlamaPack of the llama-index-packs-finchat package, versions up to v0.3.0, allows for SQL injection in the run_sql_query function of the database_agent. This vulnerability can be exploited by an attacker to inject arbitrary SQL queries, leading to remote code execution (RCE) through the use of PostgreSQL's large object functionality.
The issue is resolved by no longer officially supporting the package and moving it into the stale_packages branch on the repo, this removing it from documentation etc.
Are you affected?
Ask from here. InfraStack checks the affected versions against your stack and answers in your inbox.
InfraStack checks the affected versions against your stack and answers in Slack, with the evidence and the fix.
InfraStack checks it against your stack and answers on your report, with the evidence and the fix.
GitHub Advisory Database, CC-BY 4.0 · NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.