Vendor CVEs
Langchain AI
All CVEs
80 total · sorted by risk| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2025-64439 | Hig | 0.41 | — | 0.01 | Nov 7, 2025 | LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code… | ||
| CVE-2025-64104 | Hig | 0.40 | 7.3 | 0.00 | Oct 29, 2025 | LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Prior to 2.0.11, LangGraph's SQLite store implementation contains SQL injection vulnerabilities using direct string concatenation without… | ||
| CVE-2025-8709 | Hig | 0.40 | 7.3 | 0.00 | Oct 26, 2025 | A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators ($eq, $ne,… | ||
| CVE-2026-50181 | Hig | 0.39 | 7.1 | 0.00 | Jul 10, 2026 | Langroid is a framework for building large-language-model-powered applications. Prior to version 0.64.0, Langroid's `ReadFileTool` and `WriteFileTool` appear to treat `curr_dir` as the intended working-directory boundary for file operations. However, the tools only change the… | ||
| CVE-2026-45134 | Hig | 0.39 | 7.1 | 0.00 | May 27, 2026 | LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods (pull_prompt / pull_prompt_commit in Python, pullPrompt / pullPromptCommit in JS/TS) fetch and… | ||
| CVE-2026-28277 | Med | 0.38 | 6.8 | 0.01 | Mar 5, 2026 | 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… | ||
| CVE-2026-48121 | Med | 0.37 | 6.7 | 0.00 | Aug 4, 2026 | @langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are… | ||
| CVE-2026-27794 | Med | 0.36 | 6.6 | 0.01 | Feb 25, 2026 | LangGraph Checkpoint defines the base interface for LangGraph checkpointers. Prior to version 4.0.0, a Remote Code Execution vulnerability exists in LangGraph's caching layer when applications enable cache backends that inherit from `BaseCache` and opt nodes into caching via… | ||
| CVE-2026-27022 | Med | 0.35 | 6.5 | 0.00 | Feb 20, 2026 | @langchain/langgraph-checkpoint-redis is the Redis checkpoint and store implementation for LangGraph. A query injection vulnerability exists in the @langchain/langgraph-checkpoint-redis package's filter handling. The RedisSaver and ShallowRedisSaver classes construct RediSearch… | ||
| CVE-2026-55236 | Med | 0.31 | 5.9 | 0.00 | Sep 14, 2026 | langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, the langgraph-api run-creation path authorizes the assistant attached to a run by dispatching assistants.search with an incomplete value instead of the assistants.read event used by… | ||
| CVE-2026-55235 | Med | 0.31 | 5.9 | 0.00 | Sep 14, 2026 | langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that… | ||
| CVE-2024-1455 | Med | 0.31 | 5.9 | 0.01 | Mar 26, 2024 | A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory… | ||
| CVE-2026-40190 | Med | 0.29 | 5.6 | 0.00 | Apr 10, 2026 | 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… | ||
| CVE-2026-71433 | Med | 0.27 | 5.3 | 0.00 | Aug 6, 2026 | LangGraph Checkpoint Postgres and SQLite Checkpoint are the Postgres and SQLite implementations of LangGraph's checkpoint saver. Prior to 3.1.1, the langgraph-checkpoint-postgres and langgraph-checkpoint-sqlite packages persisted hierarchical namespaces as a dot joined string… | ||
| CVE-2026-40087 | Med | 0.27 | 5.3 | 0.00 | Apr 9, 2026 | 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… | ||
| CVE-2024-10940 | Med | 0.27 | 5.3 | 0.00 | Mar 20, 2025 | 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… | ||
| CVE-2026-59152 | Med | 0.26 | 5.0 | 0.00 | Jul 6, 2026 | LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to 0.8.18, an attacker who can send an HTTP request to a server running the LangSmith SDK's TracingMiddleware can cause that server to read an arbitrary file from its local filesystem and… | ||
| CVE-2026-55443 | Med | 0.26 | 5.1 | 0.00 | Jun 22, 2026 | 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… | ||
| CVE-2024-2965 | Med | 0.24 | 4.7 | 0.00 | Jun 6, 2024 | A Denial-of-Service (DoS) vulnerability exists in the `SitemapLoader` class of the `langchain-ai/langchain` repository, affecting all versions. The `parse_sitemap` method, responsible for parsing sitemaps and extracting URLs, lacks a mechanism to prevent infinite recursion when… | ||
| CVE-2026-14742 | Low | 0.20 | 3.1 | 0.00 | Jul 5, 2026 | A vulnerability was determined in langchain-ai langgraph up to 1.2.4. The affected element is the function _freeze of the file libs/langgraph/langgraph/_internal/_cache.py of the component Task Result Cache. This manipulation of the argument default_cache_key causes use of weak… | ||
| CVE-2026-48776 | Med | 0.20 | 4.2 | 0.00 | Jun 17, 2026 | 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… | ||
| CVE-2026-41488 | Low | 0.20 | 3.1 | 0.00 | Apr 24, 2026 | 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… | ||
| CVE-2026-27795 | Med | 0.20 | 4.1 | 0.00 | Feb 25, 2026 | 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… | ||
| CVE-2026-26019 | Med | 0.20 | 4.1 | 0.00 | Feb 11, 2026 | 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… | ||
| CVE-2026-26013 | Low | 0.17 | 3.7 | 0.00 | Feb 10, 2026 | 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… | ||
| CVE-2026-55615 | Cri | 0.00 | — | 0.00 | Jul 10, 2026 | Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is… | ||
| CVE-2026-54771 | Hig | 0.00 | 8.1 | 0.00 | Jul 10, 2026 | Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.3, a Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with `use=False,… | ||
| CVE-2026-54769 | Cri | 0.00 | 10.0 | 0.01 | Jul 10, 2026 | Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. When these agents evaluate… | ||
| CVE-2026-54760 | Cri | 0.00 | — | 0.01 | Jul 10, 2026 | Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.1, the `SQLChatAgent` SQL-injection mitigation, with default `allow_dangerous_operations=False`, combines a raw-text regex blocklist (`_DANGEROUS_SQL_PATTERNS`) with a `sqlglot`… | ||
| CVE-2024-2057 | Med | 0.00 | 6.3 | 0.01 | Mar 1, 2024 | A vulnerability was found in LangChain langchain_community 0.0.26. It has been classified as critical. Affected is the function load_local in the library libs/community/langchain_community/retrievers/tfidf.py of the component TFIDFRetriever. The manipulation leads to server-side… |
- risk 0.41cvss —epss 0.01
LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code…
- risk 0.40cvss 7.3epss 0.00
LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Prior to 2.0.11, LangGraph's SQLite store implementation contains SQL injection vulnerabilities using direct string concatenation without…
- risk 0.40cvss 7.3epss 0.00
A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators ($eq, $ne,…
- risk 0.39cvss 7.1epss 0.00
Langroid is a framework for building large-language-model-powered applications. Prior to version 0.64.0, Langroid's `ReadFileTool` and `WriteFileTool` appear to treat `curr_dir` as the intended working-directory boundary for file operations. However, the tools only change the…
- risk 0.39cvss 7.1epss 0.00
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods (pull_prompt / pull_prompt_commit in Python, pullPrompt / pullPromptCommit in JS/TS) fetch and…
- risk 0.38cvss 6.8epss 0.01
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…
- risk 0.37cvss 6.7epss 0.00
@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are…
- risk 0.36cvss 6.6epss 0.01
LangGraph Checkpoint defines the base interface for LangGraph checkpointers. Prior to version 4.0.0, a Remote Code Execution vulnerability exists in LangGraph's caching layer when applications enable cache backends that inherit from `BaseCache` and opt nodes into caching via…
- risk 0.35cvss 6.5epss 0.00
@langchain/langgraph-checkpoint-redis is the Redis checkpoint and store implementation for LangGraph. A query injection vulnerability exists in the @langchain/langgraph-checkpoint-redis package's filter handling. The RedisSaver and ShallowRedisSaver classes construct RediSearch…
- risk 0.31cvss 5.9epss 0.00
langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, the langgraph-api run-creation path authorizes the assistant attached to a run by dispatching assistants.search with an incomplete value instead of the assistants.read event used by…
- risk 0.31cvss 5.9epss 0.00
langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that…
- risk 0.31cvss 5.9epss 0.01
A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory…
- risk 0.29cvss 5.6epss 0.00
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…
- risk 0.27cvss 5.3epss 0.00
LangGraph Checkpoint Postgres and SQLite Checkpoint are the Postgres and SQLite implementations of LangGraph's checkpoint saver. Prior to 3.1.1, the langgraph-checkpoint-postgres and langgraph-checkpoint-sqlite packages persisted hierarchical namespaces as a dot joined string…
- risk 0.27cvss 5.3epss 0.00
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…
- risk 0.27cvss 5.3epss 0.00
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…
- risk 0.26cvss 5.0epss 0.00
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to 0.8.18, an attacker who can send an HTTP request to a server running the LangSmith SDK's TracingMiddleware can cause that server to read an arbitrary file from its local filesystem and…
- risk 0.26cvss 5.1epss 0.00
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…
- risk 0.24cvss 4.7epss 0.00
A Denial-of-Service (DoS) vulnerability exists in the `SitemapLoader` class of the `langchain-ai/langchain` repository, affecting all versions. The `parse_sitemap` method, responsible for parsing sitemaps and extracting URLs, lacks a mechanism to prevent infinite recursion when…
- risk 0.20cvss 3.1epss 0.00
A vulnerability was determined in langchain-ai langgraph up to 1.2.4. The affected element is the function _freeze of the file libs/langgraph/langgraph/_internal/_cache.py of the component Task Result Cache. This manipulation of the argument default_cache_key causes use of weak…
- risk 0.20cvss 4.2epss 0.00
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…
- risk 0.20cvss 3.1epss 0.00
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…
- risk 0.20cvss 4.1epss 0.00
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…
- risk 0.20cvss 4.1epss 0.00
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…
- risk 0.17cvss 3.7epss 0.00
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…
- risk 0.00cvss —epss 0.00
Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is…
- risk 0.00cvss 8.1epss 0.00
Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.3, a Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with `use=False,…
- risk 0.00cvss 10.0epss 0.01
Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. When these agents evaluate…
- risk 0.00cvss —epss 0.01
Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.1, the `SQLChatAgent` SQL-injection mitigation, with default `allow_dangerous_operations=False`, combines a raw-text regex blocklist (`_DANGEROUS_SQL_PATTERNS`) with a `sqlglot`…
- risk 0.00cvss 6.3epss 0.01
A vulnerability was found in LangChain langchain_community 0.0.26. It has been classified as critical. Affected is the function load_local in the library libs/community/langchain_community/retrievers/tfidf.py of the component TFIDFRetriever. The manipulation leads to server-side…
Page 2 of 2