彙總 langchain 相關全部產品的 CVE 與安全漏洞情報，包括 CVSS、EPSS、公開時間與漏洞情報資料。
歷史漏洞主要涉及 SQL 注入與XXE 等問題，部分漏洞可能導致 檔案覆寫，並影響 軟體部署與生產負載 相關場景。
相關漏洞資料主要來源於公開漏洞披露與安全公告，可用於評估歷史漏洞暴露面與修補優先順序。
| CVE | 摘要 | 來源 | 最高 CVSS | EPSS % | 公開時間 | 更新時間 |
|---|---|---|---|---|---|---|
| CVE-2026-55443 | LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search agent middleware that validates a starting directory but not the search pattern or the resolved target of matched files, so glob patterns and symlinks can reach files outside the configured root; prompt- | [email protected] | 5.1 | 0.17% | 2026-06-22 | 2026-06-26 |
| CVE-2026-48776 | LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. Versions 0.3.14 and prior have unsafe URL path construction through unsanitized caller-supplied identifier values used in HTTP request paths for resource operations. Without sanitization of those values, identifiers that contain characters with special meaning in URL paths could cause the resulting request to address a different resource (and potentially | [email protected] | 4.2 | 0.22% | 2026-06-17 | 2026-06-26 |
| CVE-2026-48775 | LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 4.1.0 and prior, the JsonPlusSerializer can reconstruct Python objects from JSON checkpoint payloads. Under conditions where someone could modify checkpoint bytes at rest in the backing store, the deserialization path could reconstruct objects beyond what the application expects, which could in turn result in code execution at checkpoint load time. T | [email protected] | 6.8 | 0.23% | 2026-06-16 | 2026-06-24 |
| CVE-2026-44843 | LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects="all". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime path | [email protected] | 8.2 | 0.41% | 2026-05-26 | 2026-06-17 |
| CVE-2026-41488 | LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch. | [email protected] | 3.1 | 0.16% | 2026-04-24 | 2026-06-17 |
| CVE-2026-41481 | LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTextSplitter.split_text_from_url() validated the initial URL using validate_safe_url() but then performed the fetch with requests.get() with redirects enabled (the default). Because redirect targets were not revalidated, a URL pointing to an attacker-controlled server could redirect to internal, localhost, or cloud metadata endpoints, bypassing SSRF protections. The resp | [email protected] | 6.5 | 0.26% | 2026-04-24 | 2026-06-29 |
| CVE-2026-40190 | LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to 0.5.18, the LangSmith JavaScript/TypeScript SDK (langsmith) contains an incomplete prototype pollution fix in its internally vendored lodash set() utility. The baseAssignValue() function only guards against the __proto__ key, but fails to prevent traversal via constructor.prototype. This allows an attacker who controls keys in data processed by the createAnonymizer() API to pollute Object.prototype, affecti | [email protected] | 5.6 | 0.23% | 2026-04-10 | 2026-07-07 |
| CVE-2026-40087 | LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.84 and 1.2.28, LangChain's f-string prompt-template validation was incomplete in two respects. First, some prompt template classes accepted f-string templates and formatted them without enforcing the same attribute-access validation as PromptTemplate. In particular, DictPromptTemplate and ImagePromptTemplate could accept templates containing attribute access or indexing expressions and subsequently evaluate t | [email protected] | 5.3 | 0.26% | 2026-04-09 | 2026-06-17 |
| CVE-2026-34070 | 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 chec | [email protected] | 7.5 | 1.18% | 2026-03-30 | 2026-06-29 |
| CVE-2026-28277 | LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In version 1.0.9 and prior, LangGraph checkpointers can load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker can modify checkpoint data in the backing store (for example, after a database compromise or other privileged write access to the persistence layer), they can potentially supply a crafted payload that tri | [email protected] | 6.8 | 5.22% | 2026-03-05 | 2026-06-17 |
| CVE-2026-25750 | Langchain Helm Charts are Helm charts for deploying Langchain applications on Kubernetes. Prior to langchain-ai/helm version 0.12.71, a URL parameter injection vulnerability existed in LangSmith Studio that could allow unauthorized access to user accounts through stolen authentication tokens. The vulnerability affected both LangSmith Cloud and self-hosted deployments. Authenticated LangSmith users who clicked on a specially crafted malicious link would have their bearer token, user ID, and works | [email protected] | 8.5 | 0.29% | 2026-03-04 | 2026-06-17 |
| CVE-2026-27795 | LangChain is a framework for building LLM-powered applications. Prior to version 1.1.8, a redirect-based Server-Side Request Forgery (SSRF) bypass exists in `RecursiveUrlLoader` in `@langchain/community`. The loader validates the initial URL but allows the underlying fetch to follow redirects automatically, which permits a transition from a safe public URL to an internal or metadata endpoint without revalidation. This is a bypass of the SSRF protections introduced in 1.1.14 (CVE-2026-26019). Use | [email protected] | 4.1 | 0.21% | 2026-02-25 | 2026-06-17 |
| CVE-2026-26019 | LangChain is a framework for building LLM-powered applications. Prior to 1.1.14, the RecursiveUrlLoader class in @langchain/community is a web crawler that recursively follows links from a starting URL. Its preventOutside option (enabled by default) is intended to restrict crawling to the same site as the base URL. The implementation used String.startsWith() to compare URLs, which does not perform semantic URL validation. An attacker who controls content on a crawled page could include links to | [email protected] | 4.1 | 0.37% | 2026-02-11 | 2026-06-17 |
| CVE-2026-26013 | LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input. This vulnerability is fixed in 1.2.11. | [email protected] | 3.7 | 0.38% | 2026-02-10 | 2026-06-17 |
| CVE-2024-58340 | LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service (ReDoS) vulnerability in the MRKLOutputParser.parse() method (libs/langchain/langchain/agents/mrkl/output_parser.py). The parser applies a backtracking-prone regular expression when extracting tool actions from model output. An attacker who can supply or influence the parsed text (for example via prompt injection in downstream applications that pass LLM output directly into MRKLOutputParser.parse()) can t | [email protected] | 8.7 | 0.41% | 2026-01-12 | 2026-06-17 |
| CVE-2025-68665 | LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to langchain versions 0.3.37 and 1.2.3, a serialization injection vulnerability exists in LangChain JS's toJSON() method (and subsequently when string-ifying objects using JSON.stringify(). The method did not escape objects with 'lc' keys when serializing free-form data in kwargs. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlle | [email protected] | 8.6 | 0.73% | 2025-12-23 | 2026-06-17 |
| CVE-2025-68664 | LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization r | [email protected] | 9.3 | 13.83% | 2025-12-23 | 2026-06-17 |
| CVE-2025-67644 | LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to manipulate SQL queries through metadata filter keys, affecting applications that accept untrusted metadata filter keys (not just filter values) in checkpoint search operations. The _metadata_predicate() function constructs SQL queries by | [email protected] | 7.3 | 2.07% | 2025-12-10 | 2026-06-17 |
| CVE-2025-2828 | A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (specifically, langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit) in langchain-ai/langchain version 0.0.27. This vulnerability occurs because the toolkit does not enforce restrictions on requests to remote internet addresses, allowing it to also access local addresses. As a result, an attacker could exploit this flaw to perform port scans, access local se | [email protected] | 10.0 | 14.06% | 2025-06-23 | 2026-06-17 |
| CVE-2024-8309 | A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in multi-tenant security environments, and data integrity issues. Attackers can create, update, or delete nodes and relationships without proper authorization, extract sensitive data, disrupt services, access data across dif | [email protected] | 9.8 | 13.80% | 2024-10-29 | 2026-06-17 |