LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.
oryginał ENCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:NLangchain Core
APPLangchain< 1.2.22
Powiązane podatności
Podatność deserialization injection w funkcjach dumps/dumpd LangChain Core
LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.84 and 1.2.28, LangCha...
LangChain to framework do budowania agentów i aplikacji napędzanych LLM-ami. Przed wersją 1.2.11 metoda ChatOp...
SSRF w LangChain RequestsToolkit — dostęp do sieci wewnętrznej i metadanych chmury
SQL injection przez prompt injection w LangChain GraphCypherQAChain