CVE-2025-46725: Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store
Description
Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `LanceDocChatAgent` uses pandas eval() through `compute_from_docs()`. As a result, an attacker may be able to make the agent run malicious commands through `QueryPlan.dataframe_calc]`) compromising the host system. Langroid 0.53.15 sanitizes input to the affected function by default to tackle the most common attack vectors, and added several warnings about the risky behavior in the project documentation.
Classification
CVE ID: CVE-2025-46725
CVSS Base Severity: HIGH
CVSS Base Score: 8.1
CVSS Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:U
Affected Products
Vendor: langroid
Product: langroid
Exploit Prediction Scoring System (EPSS)
EPSS Score: 0.06% (probability of being exploited)
EPSS Percentile: 19.67% (scored less or equal to compared to others)
EPSS Date: 2025-06-15 (when was this score calculated)
Stakeholder-Specific Vulnerability Categorization (SSVC)
SSVC Exploitation: none
SSVC Technical Impact: total
SSVC Automatable: true
References
https://nvd.nist.gov/vuln/detail/CVE-2025-46725https://github.com/langroid/langroid/security/advisories/GHSA-22c2-9gwg-mj59
https://github.com/langroid/langroid/commit/0d9e4a7bb3ae2eef8d38f2e970ff916599a2b2a6