| CVE ID | Title | Vendor | Product | Severity | CVSS Score | Published At | AI Analysis |
|---|---|---|---|---|---|---|---|
| CVE-2026-41488 | angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding | langchain-ai | langchain-openai | Low | 3.1 | 2026-04-24 20:57:26 | Deep Dive |
| CVE-2026-41481 | LangChain: HTMLHeaderTextSplitter.split_text_from_url SSRF Redirect Bypass | langchain-ai | langchain-text-splitters | Medium | 6.5 | 2026-04-24 20:54:28 | Deep Dive |
| CVE-2026-41182 | LangSmith SDK: Streaming token events bypass output redaction | langchain-ai | langsmith-sdk | Medium | 5.3 | 2026-04-23 00:14:21 | Deep Dive |
| CVE-2026-40190 | LangSmith Client SDKs has Prototype Pollution in langsmith-sdk via Incomplete `__proto__` Guard in Internal lodash `set()` | langchain-ai | langsmith-sdk | Medium | 5.6 | 2026-04-10 19:47:58 | Deep Dive |
| CVE-2026-40087 | LangChain has incomplete f-string validation in prompt templates | langchain-ai | langchain | Medium | 5.3 | 2026-04-09 19:34:55 | Deep Dive |
| CVE-2026-34070 | LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions | langchain-ai | langchain | High | 7.5 | 2026-03-31 02:01:49 | Deep Dive |
| CVE-2026-28277 | LangGraph: Unsafe msgpack deserialization in LangGraph checkpoint loading | langchain-ai | langgraph | Medium | 6.8 | 2026-03-05 19:10:37 | Deep Dive |
| CVE-2026-25750 | LangSmith Studio has URL Parameter Injection Vulnerability that Enables Token Theft via Malicious baseUrl | langchain-ai | helm | - | - | 2026-03-04 21:58:59 | Deep Dive |
| CVE-2026-27795 | LangChain Community: redirect chaining can lead to SSRF bypass via RecursiveUrlLoader | langchain-ai | langchainjs | Medium | 4.1 | 2026-02-25 17:30:01 | Deep Dive |
| CVE-2026-27794 | LangGraph: BaseCache Deserialization of Untrusted Data may lead to Remote Code Execution | langchain-ai | langgraph-checkpoint | Medium | 6.6 | 2026-02-25 16:53:47 | Deep Dive |
| CVE-2026-27022 | RediSearch Query Injection in @langchain/langgraph-checkpoint-redis | langchain-ai | langgraphjs | Medium | 6.5 | 2026-02-20 21:06:54 | Deep Dive |
| CVE-2026-26019 | @langchain/community affected by SSRF Bypass in RecursiveUrlLoader via insufficient URL origin validation | langchain-ai | langchainjs | Medium | 4.1 | 2026-02-11 21:11:10 | Deep Dive |
| CVE-2026-26013 | LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages | langchain-ai | langchain | Low | 3.7 | 2026-02-10 21:51:08 | Deep Dive |
| CVE-2026-25528 | LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection | langchain-ai | langsmith-sdk | Medium | 5.8 | 2026-02-09 20:08:33 | Deep Dive |
| CVE-2024-58340 | LangChain <= 0.3.1 MRKLOutputParser ReDoS | LangChain AI | LangChain | - | - | 2026-01-12 23:05:01 | Deep Dive |
| CVE-2025-68665 | LangChain serialization injection vulnerability enables secret extraction | langchain-ai | langchainjs | High | 8.6 | 2025-12-23 22:56:05 | Deep Dive |
| CVE-2025-68664 | LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs | langchain-ai | langchain | Critical | 9.3 | 2025-12-23 22:47:44 | Deep Dive |
| CVE-2025-67644 | LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method | langchain-ai | langgraph | High | 7.3 | 2025-12-10 23:37:36 | Deep Dive |
| CVE-2025-65106 | LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates | langchain-ai | langchain | 高危 | - | 2025-11-21 21:43:02 | Deep Dive |
| CVE-2025-64439 | LangGraph Checkpoint affected by RCE in "json" mode of JsonPlusSerializer | langchain-ai | langgraph | 中危 | - | 2025-11-07 20:15:22 | Deep Dive |