CVE-2024-10940Medium· 5.3▾ Sunlitlangchain-core allows unauthorized users to read arbitrary files from the host file system
▾ Sunlit zone — Low / medium · no exploitation signal
impact 29.2 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Aug 2.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via OSV
Last analysed / modified upstream
0.4%
0.4% → 0.4%
A vulnerability in langchain-core versions >=0.1.17,<0.1.53, >=0.2.0,<0.2.43, and >=0.3.0,<0.3.15 allows unauthorized users to read arbitrary files from the host file system. The issue arises from the ability to create langchain_core.prompts.ImagePromptTemplate's (and by extension langchain_core.prompts.ChatPromptTemplate's) with input variables that can read any user-specified path from the server file system. If the outputs of these prompt templates are exposed to the user, either directly or through downstream model outputs, it can lead to the exposure of sensitive information.
langchain-core >= 0.1.17, < 0.1.53langchain-core >= 0.2.0, < 0.2.43langchain-core >= 0.3.0, < 0.3.15Upgrade to a patched release:
langchain-core 0.1.53langchain-core 0.2.43langchain-core 0.3.15Connected by shared product, vendor, weakness, or advisory.
CVE-2025-68664Critical· 9.3LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
CVE-2026-40087Medium· 5.3LangChain has incomplete f-string validation in prompt templates
CVE-2026-26013Low· 3.7LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages
CVE-2024-1455Medium· 5.9LangChain's XMLOutputParser vulnerable to XML Entity Expansion