{"vulnerability": "GHSA-22C2-9GWG-MJ59", "sightings": [{"uuid": "21779323-1941-4195-b1a1-7978677a7361", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "2a075640-a300-48a4-bb44-bc6130783b9b", "vulnerability": "GHSA-22C2-9GWG-MJ59", "type": "published-proof-of-concept", "source": "https://t.me/DarkWebInformer_CVEAlerts/17024", "content": "\ud83d\udd17 DarkWebInformer.com - Cyber Threat Intelligence\n\ud83d\udccc CVE ID: CVE-2025-46725\n\ud83d\udd25 CVSS Score: 8.1 (cvssV4_0, 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)\n\ud83d\udd39 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.\n\ud83d\udccf Published: 2025-05-20T17:24:31.618Z\n\ud83d\udccf Modified: 2025-05-20T17:24:31.618Z\n\ud83d\udd17 References:\n1. https://github.com/langroid/langroid/security/advisories/GHSA-22c2-9gwg-mj59\n2. https://github.com/langroid/langroid/commit/0d9e4a7bb3ae2eef8d38f2e970ff916599a2b2a6", "creation_timestamp": "2025-05-20T17:43:47.000000Z"}]}